Representation quotient analysis
Data preparation
Preparation of dataset
library(haven)
library(mice)
library(miceadds)
library(lmtest)
library(sandwich)
library(psych)
library(foreign)
library(car)
library(mice)
library(miceadds)
library(dplyr)
library(labeling)
library(MatchThem)
library(MatchIt)
library(cobalt)
library(robustbase)
library(broom)
library(estimatr)
library(reshape)
library(reshape2)
library(ggplot2)
library(readr)
library(mitools)
library(mice)
library(miceadds)
library(cli)
library(haven)
library(MASS)
library(robustbase)
library(ggmice)
library(nnet)
library(readxl)
#Load dataset
KODAP_data_complete <- read_sav("2025-02-17_KODAP_PP_2018-2023_Wrede_Jena.sav")
length(KODAP_data_complete$Patient_ID)
## [1] 22381
#Exclude duplicate patients
KODAP_data_complete <- KODAP_data_complete[!duplicated(KODAP_data_complete$Patient_ID) & !duplicated(KODAP_data_complete$Patient_ID, fromLast = TRUE), ]
#Exclude patients < 18 year
KODAP_data_complete <- subset(KODAP_data_complete, Pat_Alter >= 18)
#Only include CBT treatments
KODAP_data_complete <- subset(KODAP_data_complete, Ther_Verfahren == 1)
#Add NAs to diagnosis variables
KODAP_data_complete$ICD1_pre_clean <- ifelse(KODAP_data_complete$ICD1_pre_clean == "" | KODAP_data_complete$ICD1_pre_clean == "-99",NA,KODAP_data_complete$ICD1_pre_clean)
KODAP_data_complete$ICD2_pre_clean <- ifelse(KODAP_data_complete$ICD2_pre_clean == "" | KODAP_data_complete$ICD2_pre_clean == "-99",NA,KODAP_data_complete$ICD2_pre_clean)
KODAP_data_complete$ICD3_pre_clean <- ifelse(KODAP_data_complete$ICD3_pre_clean == "" | KODAP_data_complete$ICD3_pre_clean == "-99",NA,KODAP_data_complete$ICD3_pre_clean)
KODAP_data_complete$ICD4_pre_clean <- ifelse(KODAP_data_complete$ICD4_pre_clean == "" | KODAP_data_complete$ICD4_pre_clean == "-99",NA,KODAP_data_complete$ICD4_pre_clean)
KODAP_data_complete$ICD5_pre_clean <- ifelse(KODAP_data_complete$ICD5_pre_clean == "" | KODAP_data_complete$ICD5_pre_clean == "-99",NA,KODAP_data_complete$ICD5_pre_clean)
#Exclude treatments that were not reimbursed by health insurances
table(KODAP_data_complete$Abschluss)
##
## 0 1 2 3 4
## 6453 10155 2345 41 67
KODAP_data_complete <- subset(KODAP_data_complete, Abschluss %in% c(0,1,2,4))
length(KODAP_data_complete$Patient_ID)
## [1] 19020
#Only include treatments between 2018 and 2023
pss2date <- function(x) as.Date(x/86400, origin = "1582-10-14")
KODAP_data_complete$Therapie_pre <- pss2date(KODAP_data_complete$Therapie_pre)
KODAP_data_complete$Beginn_Therapie <- substr(KODAP_data_complete$Therapie_pre, 1, 4)
table(KODAP_data_complete$Beginn_Therapie)
##
## 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024
## 7 10 21 79 478 2231 2938 3056 2990 2977 2886 461
KODAP_data_complete <- subset(KODAP_data_complete, Beginn_Therapie %in% c("2018", "2019", "2020", "2021", "2022", "2023"))
length(KODAP_data_complete$Patient_ID)
## [1] 17078
length(unique(KODAP_data_complete$Ambulanz_ID))
## [1] 30
table(KODAP_data_complete$Beginn_Therapie)
##
## 2018 2019 2020 2021 2022 2023
## 2231 2938 3056 2990 2977 2886
table(KODAP_data_complete$Beginn_Therapie)/length(KODAP_data_complete$Patient_ID)*100
##
## 2018 2019 2020 2021 2022 2023
## 13.06359 17.20342 17.89437 17.50790 17.43178 16.89893
KODAP_data_complete$Age_Stepped_bin <- ifelse(KODAP_data_complete$Pat_Alter %in% c(18:64), 0,
ifelse(KODAP_data_complete$Pat_Alter %in% c(65:100), 1,NA))
KODAP_data_complete$Age_Stepped <- ifelse(KODAP_data_complete$Pat_Alter %in% c(18:64), 0,
ifelse(KODAP_data_complete$Pat_Alter %in% c(65:74), 1,
ifelse(KODAP_data_complete$Pat_Alter %in% c(75:100), 2,NA)))
KODAP_data_complete$Age_Stepped_2 <- ifelse(KODAP_data_complete$Pat_Alter %in% c(18:34), 0,
ifelse(KODAP_data_complete$Pat_Alter %in% c(35:49), 1,
ifelse(KODAP_data_complete$Pat_Alter %in% c(50:64), 2,
ifelse(KODAP_data_complete$Pat_Alter %in% c(65:74), 3,
ifelse(KODAP_data_complete$Pat_Alter %in% c(75:100), 4,NA)))))
table(KODAP_data_complete$Age_Stepped)
##
## 0 1 2
## 16558 405 115
KODAP_data_complete <- subset(KODAP_data_complete, Art_Diagnoseerhebung_pre %in% c(1,2,3))
length(KODAP_data_complete$Patient_ID)
## [1] 15915
KODAP_data_complete$Missing_diagnosis <- ifelse(is.na(KODAP_data_complete$ICD1_pre_clean) == TRUE &
is.na(KODAP_data_complete$ICD2_pre_clean) == TRUE &
is.na(KODAP_data_complete$ICD3_pre_clean) == TRUE &
is.na(KODAP_data_complete$ICD4_pre_clean) == TRUE &
is.na(KODAP_data_complete$ICD5_pre_clean) == TRUE, 1,0)
KODAP_data_complete <- subset(KODAP_data_complete, Missing_diagnosis == 0)
length(KODAP_data_complete$Patient_ID)
## [1] 13635
Preparation of census data
#Age Distibution Germany
Census_data <- read_delim("15_bevoelkerungsvorausberechnung_daten.csv",
delim = ";", escape_double = FALSE, trim_ws = TRUE)
View(Census_data)
census_amount_1864_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
census_amount_1864_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
census_amount_1864_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
census_amount_1864_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
census_amount_1864_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
census_amount_1864_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
census_amount_1834_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
census_amount_1834_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
census_amount_1834_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
census_amount_1834_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
census_amount_1834_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
census_amount_1834_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
census_amount_3549_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018, c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
census_amount_3549_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
census_amount_3549_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020, c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
census_amount_3549_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
census_amount_3549_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
census_amount_3549_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
census_amount_5064_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018, c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
census_amount_5064_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
census_amount_5064_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020, c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
census_amount_5064_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
census_amount_5064_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
census_amount_5064_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
census_amount_6574_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018, c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
census_amount_6574_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
census_amount_6574_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020, c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
census_amount_6574_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
census_amount_6574_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
census_amount_6574_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
census_amount_75plus_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018, c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
census_amount_75plus_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
census_amount_75plus_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020, c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
census_amount_75plus_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
census_amount_75plus_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
census_amount_75plus_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
census_amount_65plus_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018, c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
census_amount_65plus_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
census_amount_65plus_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020, c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
census_amount_65plus_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
census_amount_65plus_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
census_amount_65plus_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
census_amount_6569_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018, c(70:74)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
census_amount_6569_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(70:74)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
census_amount_6569_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020, c(70:74)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
census_amount_6569_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(70:74)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
census_amount_6569_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(70:74)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
census_amount_6569_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(70:74)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
census_amount_7074_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018, c(75:79)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
census_amount_7074_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(75:79)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
census_amount_7074_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020, c(75:79)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
census_amount_7074_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(75:79)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
census_amount_7074_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(75:79)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
census_amount_7074_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(75:79)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
census_amount_7579_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018, c(80:84)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
census_amount_7579_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(80:84)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
census_amount_7579_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020, c(80:84)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
census_amount_7579_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(80:84)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
census_amount_7579_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(80:84)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
census_amount_7579_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(80:84)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
census_amount_80plus_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018, c(85:104)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
census_amount_80plus_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(85:104)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
census_amount_80plus_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020, c(85:104)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
census_amount_80plus_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(85:104)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
census_amount_80plus_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(85:104)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
census_amount_80plus_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(85:104)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
year_distribution_data <- as.data.frame(table(KODAP_data_complete$Beginn_Therapie))
year_distribution_data
## Var1 Freq
## 1 2018 2095
## 2 2019 2625
## 3 2020 2432
## 4 2021 2410
## 5 2022 2255
## 6 2023 1818
#Computing dataset specific census amounts:
census_amount_1864 <- (2095/13635)*census_amount_1864_2018+(2625/13635)*census_amount_1864_2019+(2432/13635)*census_amount_1864_2020+(2410/13635)*census_amount_1864_2021+(2255/13635)*census_amount_1864_2022+(1818/13635)*census_amount_1864_2023
census_amount_1834 <- (2095/13635)*census_amount_1834_2018+(2625/13635)*census_amount_1834_2019+(2432/13635)*census_amount_1834_2020+(2410/13635)*census_amount_1834_2021+(2255/13635)*census_amount_1834_2022+(1818/13635)*census_amount_1834_2023
census_amount_3549 <- (2095/13635)*census_amount_3549_2018+(2625/13635)*census_amount_3549_2019+(2432/13635)*census_amount_3549_2020+(2410/13635)*census_amount_3549_2021+(2255/13635)*census_amount_3549_2022+(1818/13635)*census_amount_3549_2023
census_amount_5064 <- (2095/13635)*census_amount_5064_2018+(2625/13635)*census_amount_5064_2019+(2432/13635)*census_amount_5064_2020+(2410/13635)*census_amount_5064_2021+(2255/13635)*census_amount_5064_2022+(1818/13635)*census_amount_5064_2023
census_amount_6574 <- (2095/13635)*census_amount_6574_2018+(2625/13635)*census_amount_6574_2019+(2432/13635)*census_amount_6574_2020+(2410/13635)*census_amount_6574_2021+(2255/13635)*census_amount_6574_2022+(1818/13635)*census_amount_6574_2023
census_amount_75plus <- (2095/13635)*census_amount_75plus_2018+(2625/13635)*census_amount_75plus_2019+(2432/13635)*census_amount_75plus_2020+(2410/13635)*census_amount_75plus_2021+(2255/13635)*census_amount_75plus_2022+(1818/13635)*census_amount_75plus_2023
census_amount_65plus <- (2095/13635)*census_amount_65plus_2018+(2625/13635)*census_amount_65plus_2019+(2432/13635)*census_amount_65plus_2020+(2410/13635)*census_amount_65plus_2021+(2255/13635)*census_amount_65plus_2022+(1818/13635)*census_amount_65plus_2023
census_amount_6569 <- (2095/13635)*census_amount_6569_2018+(2625/13635)*census_amount_6569_2019+(2432/13635)*census_amount_6569_2020+(2410/13635)*census_amount_6569_2021+(2255/13635)*census_amount_6569_2022+(1818/13635)*census_amount_6569_2023
census_amount_7074 <- (2095/13635)*census_amount_7074_2018+(2625/13635)*census_amount_7074_2019+(2432/13635)*census_amount_7074_2020+(2410/13635)*census_amount_7074_2021+(2255/13635)*census_amount_7074_2022+(1818/13635)*census_amount_7074_2023
census_amount_7579 <- (2095/13635)*census_amount_7579_2018+(2625/13635)*census_amount_7579_2019+(2432/13635)*census_amount_7579_2020+(2410/13635)*census_amount_7579_2021+(2255/13635)*census_amount_7579_2022+(1818/13635)*census_amount_7579_2023
census_amount_80plus <- (2095/13635)*census_amount_80plus_2018+(2625/13635)*census_amount_80plus_2019+(2432/13635)*census_amount_80plus_2020+(2410/13635)*census_amount_80plus_2021+(2255/13635)*census_amount_80plus_2022+(1818/13635)*census_amount_80plus_2023
#Female only
female_amount_1864_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "w", c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
female_amount_1864_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "w", c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
female_amount_1864_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "w", c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
female_amount_1864_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "w", c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
female_amount_1864_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "w" & Census_data$Variante == 1, c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
female_amount_1864_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "w" & Census_data$Variante == 1, c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
female_amount_1834_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "w", c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
female_amount_1834_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "w", c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
female_amount_1834_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "w", c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
female_amount_1834_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "w", c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
female_amount_1834_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "w" & Census_data$Variante == 1, c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
female_amount_1834_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "w" & Census_data$Variante == 1, c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
female_amount_3549_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "w", c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
female_amount_3549_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "w", c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
female_amount_3549_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "w", c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
female_amount_3549_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "w", c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
female_amount_3549_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "w" & Census_data$Variante == 1, c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
female_amount_3549_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "w" & Census_data$Variante == 1, c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
female_amount_5064_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "w", c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
female_amount_5064_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "w", c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
female_amount_5064_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "w", c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
female_amount_5064_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "w", c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
female_amount_5064_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "w" & Census_data$Variante == 1, c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
female_amount_5064_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "w" & Census_data$Variante == 1, c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
female_amount_6574_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "w", c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
female_amount_6574_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "w", c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
female_amount_6574_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "w", c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
female_amount_6574_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "w", c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
female_amount_6574_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "w" & Census_data$Variante == 1, c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
female_amount_6574_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "w" & Census_data$Variante == 1, c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
female_amount_75plus_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "w", c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
female_amount_75plus_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "w", c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
female_amount_75plus_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "w", c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
female_amount_75plus_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "w", c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
female_amount_75plus_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "w" & Census_data$Variante == 1, c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
female_amount_75plus_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "w" & Census_data$Variante == 1, c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
female_amount_65plus_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "w", c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
female_amount_65plus_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "w", c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
female_amount_65plus_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "w", c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
female_amount_65plus_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "w", c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
female_amount_65plus_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "w" & Census_data$Variante == 1, c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
female_amount_65plus_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "w" & Census_data$Variante == 1, c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
female_amount_1864 <- (2095/13635)*female_amount_1864_2018+(2625/13635)*female_amount_1864_2019+(2432/13635)*female_amount_1864_2020+(2410/13635)*female_amount_1864_2021+(2255/13635)*female_amount_1864_2022+(1818/13635)*female_amount_1864_2023
female_amount_1834 <- (2095/13635)*female_amount_1834_2018+(2625/13635)*female_amount_1834_2019+(2432/13635)*female_amount_1834_2020+(2410/13635)*female_amount_1834_2021+(2255/13635)*female_amount_1834_2022+(1818/13635)*female_amount_1834_2023
female_amount_3549 <- (2095/13635)*female_amount_3549_2018+(2625/13635)*female_amount_3549_2019+(2432/13635)*female_amount_3549_2020+(2410/13635)*female_amount_3549_2021+(2255/13635)*female_amount_3549_2022+(1818/13635)*female_amount_3549_2023
female_amount_5064 <- (2095/13635)*female_amount_5064_2018+(2625/13635)*female_amount_5064_2019+(2432/13635)*female_amount_5064_2020+(2410/13635)*female_amount_5064_2021+(2255/13635)*female_amount_5064_2022+(1818/13635)*female_amount_5064_2023
female_amount_6574 <- (2095/13635)*female_amount_6574_2018+(2625/13635)*female_amount_6574_2019+(2432/13635)*female_amount_6574_2020+(2410/13635)*female_amount_6574_2021+(2255/13635)*female_amount_6574_2022+(1818/13635)*female_amount_6574_2023
female_amount_75plus <- (2095/13635)*female_amount_75plus_2018+(2625/13635)*female_amount_75plus_2019+(2432/13635)*female_amount_75plus_2020+(2410/13635)*female_amount_75plus_2021+(2255/13635)*female_amount_75plus_2022+(1818/13635)*female_amount_75plus_2023
female_amount_65plus <- (2095/13635)*female_amount_65plus_2018+(2625/13635)*female_amount_65plus_2019+(2432/13635)*female_amount_65plus_2020+(2410/13635)*female_amount_65plus_2021+(2255/13635)*female_amount_65plus_2022+(1818/13635)*female_amount_65plus_2023
#Male only
male_amount_1864_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "m", c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
male_amount_1864_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "m", c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
male_amount_1864_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "m", c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
male_amount_1864_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "m", c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
male_amount_1864_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "m" & Census_data$Variante == 1, c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
male_amount_1864_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "m" & Census_data$Variante == 1, c(23:69)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
male_amount_1834_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "m", c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
male_amount_1834_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "m", c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
male_amount_1834_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "m", c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
male_amount_1834_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "m", c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
male_amount_1834_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "m" & Census_data$Variante == 1, c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
male_amount_1834_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "m" & Census_data$Variante == 1, c(23:39)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
male_amount_3549_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "m", c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
male_amount_3549_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "m", c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
male_amount_3549_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "m", c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
male_amount_3549_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "m", c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
male_amount_3549_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "m" & Census_data$Variante == 1, c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
male_amount_3549_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "m" & Census_data$Variante == 1, c(40:54)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
male_amount_5064_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "m", c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
male_amount_5064_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "m", c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
male_amount_5064_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "m", c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
male_amount_5064_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "m", c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
male_amount_5064_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "m" & Census_data$Variante == 1, c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
male_amount_5064_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "m" & Census_data$Variante == 1, c(55:69)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
male_amount_6574_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "m", c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
male_amount_6574_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "m", c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
male_amount_6574_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "m", c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
male_amount_6574_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "m", c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
male_amount_6574_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "m" & Census_data$Variante == 1, c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
male_amount_6574_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "m" & Census_data$Variante == 1, c(70:79)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
male_amount_75plus_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "m", c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
male_amount_75plus_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "m", c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
male_amount_75plus_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "m", c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
male_amount_75plus_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "m", c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
male_amount_75plus_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "m" & Census_data$Variante == 1, c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
male_amount_75plus_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "m" & Census_data$Variante == 1, c(80:104)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
male_amount_65plus_2018 <- sum(Census_data[Census_data$Simulationsjahr == 2018 & Census_data$mw == "m", c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2018, c(23:104)])
male_amount_65plus_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019 & Census_data$mw == "m", c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:104)])
male_amount_65plus_2020 <- sum(Census_data[Census_data$Simulationsjahr == 2020 & Census_data$mw == "m", c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2020, c(23:104)])
male_amount_65plus_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021 & Census_data$mw == "m", c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:104)])
male_amount_65plus_2022 <- sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$mw == "m" & Census_data$Variante == 1, c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2022 & Census_data$Variante == 1, c(23:104)])
male_amount_65plus_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$mw == "m" & Census_data$Variante == 1, c(70:104)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:104)])
male_amount_1864 <- (2095/13635)*male_amount_1864_2018+(2625/13635)*male_amount_1864_2019+(2432/13635)*male_amount_1864_2020+(2410/13635)*male_amount_1864_2021+(2255/13635)*male_amount_1864_2022+(1818/13635)*male_amount_1864_2023
male_amount_1834 <- (2095/13635)*male_amount_1834_2018+(2625/13635)*male_amount_1834_2019+(2432/13635)*male_amount_1834_2020+(2410/13635)*male_amount_1834_2021+(2255/13635)*male_amount_1834_2022+(1818/13635)*male_amount_1834_2023
male_amount_3549 <- (2095/13635)*male_amount_3549_2018+(2625/13635)*male_amount_3549_2019+(2432/13635)*male_amount_3549_2020+(2410/13635)*male_amount_3549_2021+(2255/13635)*male_amount_3549_2022+(1818/13635)*male_amount_3549_2023
male_amount_5064 <- (2095/13635)*male_amount_5064_2018+(2625/13635)*male_amount_5064_2019+(2432/13635)*male_amount_5064_2020+(2410/13635)*male_amount_5064_2021+(2255/13635)*male_amount_5064_2022+(1818/13635)*male_amount_5064_2023
male_amount_6574 <- (2095/13635)*male_amount_6574_2018+(2625/13635)*male_amount_6574_2019+(2432/13635)*male_amount_6574_2020+(2410/13635)*male_amount_6574_2021+(2255/13635)*male_amount_6574_2022+(1818/13635)*male_amount_6574_2023
male_amount_75plus <- (2095/13635)*male_amount_75plus_2018+(2625/13635)*male_amount_75plus_2019+(2432/13635)*male_amount_75plus_2020+(2410/13635)*male_amount_75plus_2021+(2255/13635)*male_amount_75plus_2022+(1818/13635)*male_amount_75plus_2023
male_amount_65plus <- (2095/13635)*male_amount_65plus_2018+(2625/13635)*male_amount_65plus_2019+(2432/13635)*male_amount_65plus_2020+(2410/13635)*male_amount_65plus_2021+(2255/13635)*male_amount_65plus_2022+(1818/13635)*male_amount_65plus_2023
###Rates of long-term-care dependency
GENESIS <- read_csv2("Long-term care GENESIS.csv")
View(GENESIS)
colnames(GENESIS) <- c("Gender", "Age", "2011", "2013", "2015", "2017", "2019", "2021", "2023")
#2017
census_amount_1824_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(23:29)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_2529_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(30:34)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_3034_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(35:39)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_3539_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(40:44)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_4044_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(45:49)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_4549_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(50:54)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_5054_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(55:59)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_5559_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(60:64)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_6064_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(65:69)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_6569_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(70:74)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_7074_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(75:79)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_7579_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(80:84)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_8084_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(85:89)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_8589_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(90:94)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_9094_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(95:99)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
census_amount_95plus_2017 <- sum(Census_data[Census_data$Simulationsjahr == 2017, c(100:104)])/sum(Census_data[Census_data$Simulationsjahr == 2017, "Bev"])
sum_1864_2017 <- sum(census_amount_1824_2017, census_amount_2529_2017, census_amount_3034_2017, census_amount_3539_2017, census_amount_4044_2017,
census_amount_4549_2017, census_amount_5054_2017, census_amount_5559_2017, census_amount_6064_2017)
Long_term_care_rate_1864_2017 <- ((census_amount_1824_2017/sum_1864_2017)*as.numeric(GENESIS[GENESIS$Age == "20 to under 25 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_2529_2017/sum_1864_2017)*as.numeric(GENESIS[GENESIS$Age == "25 to under 30 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_3034_2017/sum_1864_2017)*as.numeric(GENESIS[GENESIS$Age == "30 to under 35 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_3539_2017/sum_1864_2017)*as.numeric(GENESIS[GENESIS$Age == "35 to under 40 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_4044_2017/sum_1864_2017)*as.numeric(GENESIS[GENESIS$Age == "40 to under 45 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_4549_2017/sum_1864_2017)*as.numeric(GENESIS[GENESIS$Age == "45 to under 50 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_5054_2017/sum_1864_2017)*as.numeric(GENESIS[GENESIS$Age == "50 to under 55 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_5559_2017/sum_1864_2017)*as.numeric(GENESIS[GENESIS$Age == "55 to under 60 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_6064_2017/sum_1864_2017)*as.numeric(GENESIS[GENESIS$Age == "60 to under 65 years" & GENESIS$Gender == "Total", "2017"]))/100
sum_6574_2017 <- sum(census_amount_6569_2017, census_amount_7074_2017)
Long_term_care_rate_6574_2017 <- ((census_amount_6569_2017/sum_6574_2017)*as.numeric(GENESIS[GENESIS$Age == "65 to under 70 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_7074_2017/sum_6574_2017)*as.numeric(GENESIS[GENESIS$Age == "70 to under 75 years" & GENESIS$Gender == "Total", "2017"]))/100
sum_75plus_2017 <- sum(census_amount_7579_2017, census_amount_8084_2017, census_amount_8589_2017, census_amount_9094_2017, census_amount_95plus_2017)
Long_term_care_rate_75plus_2017 <-((census_amount_7579_2017/sum_75plus_2017)*as.numeric(GENESIS[GENESIS$Age == "75 to under 80 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_8084_2017/sum_75plus_2017)*as.numeric(GENESIS[GENESIS$Age == "80 to under 85 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_8589_2017/sum_75plus_2017)*as.numeric(GENESIS[GENESIS$Age == "85 to under 90 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_9094_2017/sum_75plus_2017)*as.numeric(GENESIS[GENESIS$Age == "90 to under 95 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_95plus_2017/sum_75plus_2017)*as.numeric(GENESIS[GENESIS$Age == "95 years and over" & GENESIS$Gender == "Total", "2017"]))/100
sum_65plus_2017 <- sum(census_amount_6569_2017, census_amount_7074_2017,census_amount_7579_2017, census_amount_8084_2017, census_amount_8589_2017, census_amount_9094_2017, census_amount_95plus_2017)
Long_term_care_rate_65plus_2017 <-((census_amount_6569_2017/sum_65plus_2017)*as.numeric(GENESIS[GENESIS$Age == "65 to under 70 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_7074_2017/sum_65plus_2017)*as.numeric(GENESIS[GENESIS$Age == "70 to under 75 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_7579_2017/sum_65plus_2017)*as.numeric(GENESIS[GENESIS$Age == "75 to under 80 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_8084_2017/sum_65plus_2017)*as.numeric(GENESIS[GENESIS$Age == "80 to under 85 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_8589_2017/sum_65plus_2017)*as.numeric(GENESIS[GENESIS$Age == "85 to under 90 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_9094_2017/sum_65plus_2017)*as.numeric(GENESIS[GENESIS$Age == "90 to under 95 years" & GENESIS$Gender == "Total", "2017"])+
(census_amount_95plus_2017/sum_65plus_2017)*as.numeric(GENESIS[GENESIS$Age == "95 years and over" & GENESIS$Gender == "Total", "2017"]))/100
#2019
census_amount_1824_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(23:29)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_2529_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(30:34)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_3034_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(35:39)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_3539_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(40:44)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_4044_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(45:49)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_4549_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(50:54)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_5054_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(55:59)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_5559_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(60:64)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_6064_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(65:69)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_6569_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(70:74)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_7074_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(75:79)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_7579_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(80:84)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_8084_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(85:89)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_8589_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(90:94)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_9094_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(95:99)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
census_amount_95plus_2019 <- sum(Census_data[Census_data$Simulationsjahr == 2019, c(100:104)])/sum(Census_data[Census_data$Simulationsjahr == 2019, "Bev"])
sum_1864_2019 <- sum(census_amount_1824_2019, census_amount_2529_2019, census_amount_3034_2019, census_amount_3539_2019, census_amount_4044_2019,
census_amount_4549_2019, census_amount_5054_2019, census_amount_5559_2019, census_amount_6064_2019)
Long_term_care_rate_1864_2019 <- ((census_amount_1824_2019/sum_1864_2019)*as.numeric(GENESIS[GENESIS$Age == "20 to under 25 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_2529_2019/sum_1864_2019)*as.numeric(GENESIS[GENESIS$Age == "25 to under 30 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_3034_2019/sum_1864_2019)*as.numeric(GENESIS[GENESIS$Age == "30 to under 35 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_3539_2019/sum_1864_2019)*as.numeric(GENESIS[GENESIS$Age == "35 to under 40 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_4044_2019/sum_1864_2019)*as.numeric(GENESIS[GENESIS$Age == "40 to under 45 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_4549_2019/sum_1864_2019)*as.numeric(GENESIS[GENESIS$Age == "45 to under 50 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_5054_2019/sum_1864_2019)*as.numeric(GENESIS[GENESIS$Age == "50 to under 55 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_5559_2019/sum_1864_2019)*as.numeric(GENESIS[GENESIS$Age == "55 to under 60 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_6064_2019/sum_1864_2019)*as.numeric(GENESIS[GENESIS$Age == "60 to under 65 years" & GENESIS$Gender == "Total", "2019"]))/100
sum_6574_2019 <- sum(census_amount_6569_2019, census_amount_7074_2019)
Long_term_care_rate_6574_2019 <- ((census_amount_6569_2019/sum_6574_2019)*as.numeric(GENESIS[GENESIS$Age == "65 to under 70 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_7074_2019/sum_6574_2019)*as.numeric(GENESIS[GENESIS$Age == "70 to under 75 years" & GENESIS$Gender == "Total", "2019"]))/100
sum_75plus_2019 <- sum(census_amount_7579_2019, census_amount_8084_2019, census_amount_8589_2019, census_amount_9094_2019, census_amount_95plus_2019)
Long_term_care_rate_75plus_2019 <-((census_amount_7579_2019/sum_75plus_2019)*as.numeric(GENESIS[GENESIS$Age == "75 to under 80 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_8084_2019/sum_75plus_2019)*as.numeric(GENESIS[GENESIS$Age == "80 to under 85 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_8589_2019/sum_75plus_2019)*as.numeric(GENESIS[GENESIS$Age == "85 to under 90 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_9094_2019/sum_75plus_2019)*as.numeric(GENESIS[GENESIS$Age == "90 to under 95 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_95plus_2019/sum_75plus_2019)*as.numeric(GENESIS[GENESIS$Age == "95 years and over" & GENESIS$Gender == "Total", "2019"]))/100
sum_65plus_2019 <- sum(census_amount_6569_2019, census_amount_7074_2019,census_amount_7579_2019, census_amount_8084_2019, census_amount_8589_2019, census_amount_9094_2019, census_amount_95plus_2019)
Long_term_care_rate_65plus_2019 <-((census_amount_6569_2019/sum_65plus_2019)*as.numeric(GENESIS[GENESIS$Age == "65 to under 70 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_7074_2019/sum_65plus_2019)*as.numeric(GENESIS[GENESIS$Age == "70 to under 75 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_7579_2019/sum_65plus_2019)*as.numeric(GENESIS[GENESIS$Age == "75 to under 80 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_8084_2019/sum_65plus_2019)*as.numeric(GENESIS[GENESIS$Age == "80 to under 85 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_8589_2019/sum_65plus_2019)*as.numeric(GENESIS[GENESIS$Age == "85 to under 90 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_9094_2019/sum_65plus_2019)*as.numeric(GENESIS[GENESIS$Age == "90 to under 95 years" & GENESIS$Gender == "Total", "2019"])+
(census_amount_95plus_2019/sum_65plus_2019)*as.numeric(GENESIS[GENESIS$Age == "95 years and over" & GENESIS$Gender == "Total", "2019"]))/100
#2021
census_amount_1824_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(23:29)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_2529_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(30:34)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_3034_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(35:39)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_3539_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(40:44)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_4044_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(45:49)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_4549_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(50:54)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_5054_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(55:59)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_5559_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(60:64)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_6064_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(65:69)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_6569_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(70:74)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_7074_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(75:79)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_7579_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(80:84)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_8084_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(85:89)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_8589_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(90:94)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_9094_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(95:99)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
census_amount_95plus_2021 <- sum(Census_data[Census_data$Simulationsjahr == 2021, c(100:104)])/sum(Census_data[Census_data$Simulationsjahr == 2021, "Bev"])
sum_1864_2021 <- sum(census_amount_1824_2021, census_amount_2529_2021, census_amount_3034_2021, census_amount_3539_2021, census_amount_4044_2021,
census_amount_4549_2021, census_amount_5054_2021, census_amount_5559_2021, census_amount_6064_2021)
Long_term_care_rate_1864_2021 <- ((census_amount_1824_2021/sum_1864_2021)*as.numeric(GENESIS[GENESIS$Age == "20 to under 25 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_2529_2021/sum_1864_2021)*as.numeric(GENESIS[GENESIS$Age == "25 to under 30 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_3034_2021/sum_1864_2021)*as.numeric(GENESIS[GENESIS$Age == "30 to under 35 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_3539_2021/sum_1864_2021)*as.numeric(GENESIS[GENESIS$Age == "35 to under 40 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_4044_2021/sum_1864_2021)*as.numeric(GENESIS[GENESIS$Age == "40 to under 45 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_4549_2021/sum_1864_2021)*as.numeric(GENESIS[GENESIS$Age == "45 to under 50 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_5054_2021/sum_1864_2021)*as.numeric(GENESIS[GENESIS$Age == "50 to under 55 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_5559_2021/sum_1864_2021)*as.numeric(GENESIS[GENESIS$Age == "55 to under 60 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_6064_2021/sum_1864_2021)*as.numeric(GENESIS[GENESIS$Age == "60 to under 65 years" & GENESIS$Gender == "Total", "2021"]))/100
sum_6574_2021 <- sum(census_amount_6569_2021, census_amount_7074_2021)
Long_term_care_rate_6574_2021 <- ((census_amount_6569_2021/sum_6574_2021)*as.numeric(GENESIS[GENESIS$Age == "65 to under 70 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_7074_2021/sum_6574_2021)*as.numeric(GENESIS[GENESIS$Age == "70 to under 75 years" & GENESIS$Gender == "Total", "2021"]))/100
sum_75plus_2021 <- sum(census_amount_7579_2021, census_amount_8084_2021, census_amount_8589_2021, census_amount_9094_2021, census_amount_95plus_2021)
Long_term_care_rate_75plus_2021 <-((census_amount_7579_2021/sum_75plus_2021)*as.numeric(GENESIS[GENESIS$Age == "75 to under 80 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_8084_2021/sum_75plus_2021)*as.numeric(GENESIS[GENESIS$Age == "80 to under 85 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_8589_2021/sum_75plus_2021)*as.numeric(GENESIS[GENESIS$Age == "85 to under 90 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_9094_2021/sum_75plus_2021)*as.numeric(GENESIS[GENESIS$Age == "90 to under 95 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_95plus_2021/sum_75plus_2021)*as.numeric(GENESIS[GENESIS$Age == "95 years and over" & GENESIS$Gender == "Total", "2021"]))/100
sum_65plus_2021 <- sum(census_amount_6569_2021, census_amount_7074_2021,census_amount_7579_2021, census_amount_8084_2021, census_amount_8589_2021, census_amount_9094_2021, census_amount_95plus_2021)
Long_term_care_rate_65plus_2021 <-((census_amount_6569_2021/sum_65plus_2021)*as.numeric(GENESIS[GENESIS$Age == "65 to under 70 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_7074_2021/sum_65plus_2021)*as.numeric(GENESIS[GENESIS$Age == "70 to under 75 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_7579_2021/sum_65plus_2021)*as.numeric(GENESIS[GENESIS$Age == "75 to under 80 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_8084_2021/sum_65plus_2021)*as.numeric(GENESIS[GENESIS$Age == "80 to under 85 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_8589_2021/sum_65plus_2021)*as.numeric(GENESIS[GENESIS$Age == "85 to under 90 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_9094_2021/sum_65plus_2021)*as.numeric(GENESIS[GENESIS$Age == "90 to under 95 years" & GENESIS$Gender == "Total", "2021"])+
(census_amount_95plus_2021/sum_65plus_2021)*as.numeric(GENESIS[GENESIS$Age == "95 years and over" & GENESIS$Gender == "Total", "2021"]))/100
#2023
census_amount_1824_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(23:29)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_2529_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(30:34)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_3034_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(35:39)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_3539_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(40:44)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_4044_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(45:49)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_4549_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(50:54)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_5054_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(55:59)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_5559_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(60:64)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_6064_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(65:69)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_6569_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(70:74)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_7074_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(75:79)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_7579_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(80:84)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_8084_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(85:89)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_8589_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(90:94)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_9094_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(95:99)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
census_amount_95plus_2023 <- sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, c(100:104)])/sum(Census_data[Census_data$Simulationsjahr == 2023 & Census_data$Variante == 1, "Bev"])
sum_1864_2023 <- sum(census_amount_1824_2023, census_amount_2529_2023, census_amount_3034_2023, census_amount_3539_2023, census_amount_4044_2023,
census_amount_4549_2023, census_amount_5054_2023, census_amount_5559_2023, census_amount_6064_2023)
Long_term_care_rate_1864_2023 <- ((census_amount_1824_2023/sum_1864_2023)*as.numeric(GENESIS[GENESIS$Age == "20 to under 25 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_2529_2023/sum_1864_2023)*as.numeric(GENESIS[GENESIS$Age == "25 to under 30 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_3034_2023/sum_1864_2023)*as.numeric(GENESIS[GENESIS$Age == "30 to under 35 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_3539_2023/sum_1864_2023)*as.numeric(GENESIS[GENESIS$Age == "35 to under 40 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_4044_2023/sum_1864_2023)*as.numeric(GENESIS[GENESIS$Age == "40 to under 45 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_4549_2023/sum_1864_2023)*as.numeric(GENESIS[GENESIS$Age == "45 to under 50 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_5054_2023/sum_1864_2023)*as.numeric(GENESIS[GENESIS$Age == "50 to under 55 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_5559_2023/sum_1864_2023)*as.numeric(GENESIS[GENESIS$Age == "55 to under 60 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_6064_2023/sum_1864_2023)*as.numeric(GENESIS[GENESIS$Age == "60 to under 65 years" & GENESIS$Gender == "Total", "2023"]))/100
sum_6574_2023 <- sum(census_amount_6569_2023, census_amount_7074_2023)
Long_term_care_rate_6574_2023 <- ((census_amount_6569_2023/sum_6574_2023)*as.numeric(GENESIS[GENESIS$Age == "65 to under 70 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_7074_2023/sum_6574_2023)*as.numeric(GENESIS[GENESIS$Age == "70 to under 75 years" & GENESIS$Gender == "Total", "2023"]))/100
sum_75plus_2023 <- sum(census_amount_7579_2023, census_amount_8084_2023, census_amount_8589_2023, census_amount_9094_2023, census_amount_95plus_2023)
Long_term_care_rate_75plus_2023 <-((census_amount_7579_2023/sum_75plus_2023)*as.numeric(GENESIS[GENESIS$Age == "75 to under 80 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_8084_2023/sum_75plus_2023)*as.numeric(GENESIS[GENESIS$Age == "80 to under 85 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_8589_2023/sum_75plus_2023)*as.numeric(GENESIS[GENESIS$Age == "85 to under 90 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_9094_2023/sum_75plus_2023)*as.numeric(GENESIS[GENESIS$Age == "90 to under 95 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_95plus_2023/sum_75plus_2023)*as.numeric(GENESIS[GENESIS$Age == "95 years and over" & GENESIS$Gender == "Total", "2023"]))/100
sum_65plus_2023 <- sum(census_amount_6569_2023, census_amount_7074_2023,census_amount_7579_2023, census_amount_8084_2023, census_amount_8589_2023, census_amount_9094_2023, census_amount_95plus_2023)
Long_term_care_rate_65plus_2023 <-((census_amount_6569_2023/sum_65plus_2023)*as.numeric(GENESIS[GENESIS$Age == "65 to under 70 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_7074_2023/sum_65plus_2023)*as.numeric(GENESIS[GENESIS$Age == "70 to under 75 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_7579_2023/sum_65plus_2023)*as.numeric(GENESIS[GENESIS$Age == "75 to under 80 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_8084_2023/sum_65plus_2023)*as.numeric(GENESIS[GENESIS$Age == "80 to under 85 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_8589_2023/sum_65plus_2023)*as.numeric(GENESIS[GENESIS$Age == "85 to under 90 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_9094_2023/sum_65plus_2023)*as.numeric(GENESIS[GENESIS$Age == "90 to under 95 years" & GENESIS$Gender == "Total", "2023"])+
(census_amount_95plus_2023/sum_65plus_2023)*as.numeric(GENESIS[GENESIS$Age == "95 years and over" & GENESIS$Gender == "Total", "2023"]))/100
Long_term_care_rate_1864_2017
## [1] 0.009617073
Long_term_care_rate_1864_2019
## [1] 0.01208859
Long_term_care_rate_1864_2021
## [1] 0.01534732
Long_term_care_rate_1864_2023
## [1] 0.01787395
Long_term_care_rate_6574_2017
## [1] 0.04928208
Long_term_care_rate_6574_2019
## [1] 0.05923031
Long_term_care_rate_6574_2021
## [1] 0.07348887
Long_term_care_rate_6574_2023
## [1] 0.08456034
Long_term_care_rate_75plus_2017
## [1] 0.2512004
Long_term_care_rate_75plus_2019
## [1] 0.2922611
Long_term_care_rate_75plus_2021
## [1] 0.3477314
Long_term_care_rate_75plus_2023
## [1] 0.3903115
year_distribution_data <- as.data.frame(table(KODAP_data_complete$Beginn_Therapie))
Long_term_care_rate_1864_average <- (year_distribution_data[year_distribution_data$Var1 == 2018, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_1864_2017+
(year_distribution_data[year_distribution_data$Var1 == 2019, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_1864_2019+
(year_distribution_data[year_distribution_data$Var1 == 2020, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_1864_2019+
(year_distribution_data[year_distribution_data$Var1 == 2021, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_1864_2021+
(year_distribution_data[year_distribution_data$Var1 == 2022, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_1864_2021+
(year_distribution_data[year_distribution_data$Var1 == 2023, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_1864_2023
Long_term_care_rate_6574_average <- (year_distribution_data[year_distribution_data$Var1 == 2018, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_6574_2017+
(year_distribution_data[year_distribution_data$Var1 == 2019, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_6574_2019+
(year_distribution_data[year_distribution_data$Var1 == 2020, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_6574_2019+
(year_distribution_data[year_distribution_data$Var1 == 2021, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_6574_2021+
(year_distribution_data[year_distribution_data$Var1 == 2022, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_6574_2021+
(year_distribution_data[year_distribution_data$Var1 == 2023, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_6574_2023
Long_term_care_rate_75plus_average <- (year_distribution_data[year_distribution_data$Var1 == 2018, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_75plus_2017+
(year_distribution_data[year_distribution_data$Var1 == 2019, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_75plus_2019+
(year_distribution_data[year_distribution_data$Var1 == 2020, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_75plus_2019+
(year_distribution_data[year_distribution_data$Var1 == 2021, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_75plus_2021+
(year_distribution_data[year_distribution_data$Var1 == 2022, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_75plus_2021+
(year_distribution_data[year_distribution_data$Var1 == 2023, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_75plus_2023
Long_term_care_rate_65plus_average <- (year_distribution_data[year_distribution_data$Var1 == 2018, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_65plus_2017+
(year_distribution_data[year_distribution_data$Var1 == 2019, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_65plus_2019+
(year_distribution_data[year_distribution_data$Var1 == 2020, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_65plus_2019+
(year_distribution_data[year_distribution_data$Var1 == 2021, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_65plus_2021+
(year_distribution_data[year_distribution_data$Var1 == 2022, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_65plus_2021+
(year_distribution_data[year_distribution_data$Var1 == 2023, "Freq"]/sum(year_distribution_data$Freq))*Long_term_care_rate_65plus_2023
Main Analyses
#Read prevalence estimates
Prevalence_estimates <- read_excel("Prevalence_estimates.xlsx")
Prevalence_estimates
## # A tibble: 17 × 6
## Diagnosis `1834y` `3549y` `5064y` `6574y` `75yplus`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Any mental disorder 35.8 28 26.4 19.6 19.6
## 2 Any mood disorder 15.1 10.3 7 5.9 5.9
## 3 Major Depressive Disorder 10 7.2 5.2 4.4 4.4
## 4 Dysthymia 2.1 1.7 1.3 1.6 1.6
## 5 Any anxiety disorder 18.1 16.2 15.3 11.1 11.1
## 6 Panic disorder/Agoraphobia 4.2 4.1 4.1 3.5 3.5
## 7 Social phobia 4.6 3.1 2.2 0.7 0.7
## 8 Specific phobias 12.3 9.5 10.9 8.4 8.4
## 9 GAD 3.3 2 2.3 1.3 1.3
## 10 OCD 7.2 3.6 2.2 1.1 1.1
## 11 PTSD 3.7 2.5 1 1.8 1.8
## 12 Any somatoform disorder 4.2 3.8 3.6 2.1 2.1
## 13 Somatization disorder 0.9 0.6 0.9 0.8 0.8
## 14 Pain disorder 4 3.8 3 1.6 1.6
## 15 Eating disorders 2.3 0.5 0.7 0.4 0.4
## 16 Substance use disorders 8.4 5.9 5.5 2.5 2.5
## 17 Psychotic disorders 4.2 2.2 2.5 1.3 1.3
##################
#####Analyses#####
##################
#####################
#Any Mental Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 81.0 9.3 9.7
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete$Patient_ID)
Observation
## [1] 13218 324 93
round(Observation/length(KODAP_data_complete$Patient_ID)*100, 1)
## [1] 96.9 2.4 0.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 2272.7, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.482197e-323
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.860477e-234
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.482197e-323
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.19671990 0.25585825 0.07026915
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 12368, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02130213 0.02649473
## sample estimates:
## p
## 0.02376238
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574, 2)
## [1] 0.23 0.29
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 13264, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005538338 0.008388176
## sample estimates:
## p
## 0.006820682
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.06 0.09
#####################
#Any Mood Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 83.4 8.1 8.5
KODAP_data_complete_any_mood_disorder <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung"),]
length(KODAP_data_complete_any_mood_disorder$Patient_ID)
## [1] 8244
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_mood_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_mood_disorder$Patient_ID)
Observation
## [1] 8027 179 38
round(Observation/length(KODAP_data_complete_any_mood_disorder$Patient_ID)*100,1)
## [1] 97.4 2.2 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 1174.8, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.482197e-323
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.61793e-118
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.096773e-252
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.16716254 0.26786863 0.05441013
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 7541.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01872596 0.02515365
## sample estimates:
## p
## 0.02171276
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.27
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.23 0.31
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 8090.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003309074 0.006390114
## sample estimates:
## p
## 0.004609413
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.04 0.08
###########################
#Major Depressive Disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 82.4 8.6 9.0
KODAP_data_complete_MDD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD2_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD3_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD4_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert")|
KODAP_data_complete$ICD5_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert"),]
length(KODAP_data_complete_MDD$Patient_ID)
## [1] 7460
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_MDD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_MDD$Patient_ID)
Observation
## [1] 7261 163 36
round(Observation/length(KODAP_data_complete_MDD$Patient_ID)*100,1)
## [1] 97.3 2.2 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 1162.4, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 9.582918e-120
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.973743e-244
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.18153500 0.25357980 0.05358668
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 6820.3, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01870821 0.02549363
## sample estimates:
## p
## 0.02184987
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.25
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.22 0.30
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 7314.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003431670 0.006750952
## sample estimates:
## p
## 0.004825737
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.04 0.07
###########################
#########Dysthymia#########
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 74.6 12.4 13.0
KODAP_data_complete_Dysthymia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD2_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD3_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD4_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD5_pre_clean %in% c("F34.1", "F34.10"),]
length(KODAP_data_complete_Dysthymia$Patient_ID)
## [1] 958
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Dysthymia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Dysthymia$Patient_ID)
Observation
## [1] 935 22 1
round(Observation/length(KODAP_data_complete_Dysthymia$Patient_ID)*100,1)
## [1] 97.6 2.3 0.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 269.65, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 9.823106e-87
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.899135e-29
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 8.711903e-56
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.308640900 0.184762252 0.008035592
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 870.11, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01479694 0.03514765
## sample estimates:
## p
## 0.02296451
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.18
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.12 0.28
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 952.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 5.449108e-05 6.751188e-03
## sample estimates:
## p
## 0.001043841
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.01
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.05
###########################
##Any anxiety disorder#####
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 80.6 9.5 9.9
KODAP_data_complete_any_anx_disorder <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen"),]
length(KODAP_data_complete_any_anx_disorder$Patient_ID)
## [1] 4453
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_anx_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_anx_disorder$Patient_ID)
Observation
## [1] 4318 106 29
round(Observation/length(KODAP_data_complete_any_anx_disorder$Patient_ID)*100,1)
## [1] 97.0 2.4 0.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 772.5, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 5.244667e-240
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.363829e-80
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.210344e-155
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.20357702 0.25051327 0.06557679
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 4037.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01961854 0.02883120
## sample estimates:
## p
## 0.02380418
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.25
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.21 0.30
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 4335.8, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004446095 0.009469305
## sample estimates:
## p
## 0.006512464
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.04 0.10
#################################
##Panic Disorder/Agoraphobia#####
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 76.7 11.4 11.9
KODAP_data_complete_PanicAgora <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung"),]
length(KODAP_data_complete_PanicAgora$Patient_ID)
## [1] 1456
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PanicAgora$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PanicAgora$Patient_ID)
Observation
## [1] 1400 47 9
round(Observation/length(KODAP_data_complete_PanicAgora$Patient_ID)*100,1)
## [1] 96.2 3.2 0.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 312.33, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.114495e-94
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.321778e-29
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 6.078787e-65
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.25323710 0.28363345 0.05196721
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1272.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02406506 0.04304906
## sample estimates:
## p
## 0.03228022
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.28
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.21 0.38
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1418.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003019616 0.012152642
## sample estimates:
## p
## 0.006181319
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.10
#################################
##########Social phobia##########
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 92.8 3.5 3.7
KODAP_data_complete_socialphobia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.1 Soziale Phobie"),]
length(KODAP_data_complete_socialphobia$Patient_ID)
## [1] 1850
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_socialphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_socialphobia$Patient_ID)
Observation
## [1] 1830 16 4
round(Observation/length(KODAP_data_complete_socialphobia$Patient_ID)*100,1)
## [1] 98.9 0.9 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 103.92, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 7.089412e-35
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.300956e-12
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 6.342283e-24
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.06542385 0.24719537 0.05912997
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1784.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005124665 0.014335622
## sample estimates:
## p
## 0.008648649
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.25
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.15 0.41
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1832, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0006928545 0.0059315037
## sample estimates:
## p
## 0.002162162
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.06
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.02 0.16
#################################
##########Specific phobia##########
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 78.4 10.6 11.0
KODAP_data_complete_specificphobia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.2 Spezifische Phobie"),]
length(KODAP_data_complete_specificphobia$Patient_ID)
## [1] 703
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_specificphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_specificphobia$Patient_ID)
Observation
## [1] 678 22 3
round(Observation/length(KODAP_data_complete_specificphobia$Patient_ID)*100,1)
## [1] 96.4 3.1 0.4
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 137.53, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.072222e-42
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 6.419946e-13
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.446374e-30
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.22992128 0.29650350 0.03868617
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 615.88, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02018695 0.04777189
## sample estimates:
## p
## 0.03129445
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.3
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.19 0.45
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 689.07, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.001102765 0.013513634
## sample estimates:
## p
## 0.004267425
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.04
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.12
################################################
##########Generalized Anxiety Disorder##########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 84.5 7.6 7.9
KODAP_data_complete_GAD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F41.1 Generalisierte Angststörung"),]
length(KODAP_data_complete_GAD$Patient_ID)
## [1] 552
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_GAD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_GAD$Patient_ID)
Observation
## [1] 526 20 6
round(Observation/length(KODAP_data_complete_GAD$Patient_ID)*100,1)
## [1] 95.3 3.6 1.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 51.696, df = 2, p-value = 5.946e-12
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 5.844488e-15
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.0004446198
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.319313e-12
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1279988 0.4773477 0.1370198
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 473.05, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02285853 0.05637906
## sample estimates:
## p
## 0.03623188
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.48
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.30 0.74
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 526.31, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004426108 0.024731112
## sample estimates:
## p
## 0.01086957
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.14
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.06 0.31
################################################
##########Obsessive compulsive disorders########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 91.5 4.1 4.3
KODAP_data_complete_OCD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F42.X Zwangsstörung"),]
length(KODAP_data_complete_OCD$Patient_ID)
## [1] 791
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_OCD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_OCD$Patient_ID)
Observation
## [1] 778 11 2
round(Observation/length(KODAP_data_complete_OCD$Patient_ID)*100,1)
## [1] 98.4 1.4 0.3
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 48.952, df = 2, p-value = 2.345e-11
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 7.126015e-16
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.558771e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.09123e-12
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.07474006 0.33524804 0.05832179
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 745.67, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.007329893 0.025530476
## sample estimates:
## p
## 0.01390645
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.34
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.18 0.62
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 781.03, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0004380695 0.0101435327
## sample estimates:
## p
## 0.002528445
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.06
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.23
################################################
##########Post traumatic stress disorder########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 78.3 10.6 11.1
KODAP_data_complete_PTSD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung"),]
length(KODAP_data_complete_PTSD$Patient_ID)
## [1] 1067
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PTSD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PTSD$Patient_ID)
Observation
## [1] 1052 13 2
round(Observation/length(KODAP_data_complete_PTSD$Patient_ID)*100,1)
## [1] 98.6 1.2 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 258.38, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.664279e-88
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.194624e-34
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.148891e-50
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.25840984 0.11508209 0.01694032
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1013.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.006788272 0.021319397
## sample estimates:
## p
## 0.01218369
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.12
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.06 0.20
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1057, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0003247314 0.0075301326
## sample estimates:
## p
## 0.001874414
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.02
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.07
################################################
##########Any somatoform Disorders##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 83.7 8.0 8.3
KODAP_data_complete_Somatoform <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F45.X Somatoforme Störungen"),]
length(KODAP_data_complete_Somatoform$Patient_ID)
## [1] 1074
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Somatoform$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Somatoform$Patient_ID)
Observation
## [1] 1009 48 17
round(Observation/length(KODAP_data_complete_Somatoform$Patient_ID)*100,1)
## [1] 93.9 4.5 1.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 88.963, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 8.645902e-24
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.828896e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.153289e-21
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1227562 0.5599319 0.1897449
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 888.76, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03347037 0.05928157
## sample estimates:
## p
## 0.04469274
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.56
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.42 0.74
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1005.1, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.009547387 0.025770512
## sample estimates:
## p
## 0.01582868
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.19
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.11 0.31
################################################
##########Somatization disorder##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 73.8 12.8 13.4
KODAP_data_complete_Somatization <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD2_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD3_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD4_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD5_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10"),]
length(KODAP_data_complete_Somatization$Patient_ID)
## [1] 211
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Somatization$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Somatization$Patient_ID)
Observation
## [1] 203 7 1
round(Observation/length(KODAP_data_complete_Somatization$Patient_ID)*100,1)
## [1] 96.2 3.3 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 55.336, df = 2, p-value = 9.636e-13
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.943582e-17
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.177964e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.182352e-11
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.30288177 0.25938667 0.03545495
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 182.07, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01461394 0.06996360
## sample estimates:
## p
## 0.03317536
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.11 0.55
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 205.04, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0002474437 0.0302007408
## sample estimates:
## p
## 0.004739336
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.04
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.23
################################################
##########Pain disorder##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 86.2 6.8 7.1
KODAP_data_complete_Pain <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD2_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD3_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD4_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD5_pre_clean %in% c("F45.4","F45.40", "F45.41"),]
length(KODAP_data_complete_Pain$Patient_ID)
## [1] 508
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Pain$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Pain$Patient_ID)
Observation
## [1] 465 30 13
round(Observation/length(KODAP_data_complete_Pain$Patient_ID)*100,1)
## [1] 91.5 5.9 2.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 16.893, df = 2, p-value = 0.0002146
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0.0007199377
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.441711
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.690537e-05
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0623855 0.8726746 0.3618277
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 393.32, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.04085658 0.08418493
## sample estimates:
## p
## 0.05905512
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.87
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.60 1.24
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 455.44, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01428679 0.04450754
## sample estimates:
## p
## 0.02559055
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.36
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.20 0.63
################################################
##########Eating disorders##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 89.0 5.4 5.6
KODAP_data_complete_Eating <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F50.X Essstörung"),]
length(KODAP_data_complete_Eating$Patient_ID)
## [1] 857
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Eating$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Eating$Patient_ID)
Observation
## [1] 849 8
Observation[3] <- 0
Observation
## [1] 849 8 0
round(Observation/length(KODAP_data_complete_Eating$Patient_ID)*100,1)
## [1] 99.1 0.9 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 89.395, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 8.208025e-32
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.213906e-11
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.441333e-21
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1130814 0.1735878 0.0000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 823.34, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004346906 0.019076925
## sample estimates:
## p
## 0.009334889
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.17
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.08 0.35
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 855, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.000000000 0.005563187
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.0 0.1
#########################################
##########Substance-use disorders########
#########################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 88.0 5.9 6.1
KODAP_data_complete_SubstanceUse <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen"),]
length(KODAP_data_complete_SubstanceUse$Patient_ID)
## [1] 764
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_SubstanceUse$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_SubstanceUse$Patient_ID)
Observation
## [1] 748 15 1
round(Observation/length(KODAP_data_complete_SubstanceUse$Patient_ID)*100,1)
## [1] 97.9 2.0 0.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 73.277, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.93638e-23
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 8.330415e-07
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.308868e-19
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1126184 0.3344931 0.0213365
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 703.26, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01143871 0.03294463
## sample estimates:
## p
## 0.01963351
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.33
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.19 0.56
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 758.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 6.832858e-05 8.456433e-03
## sample estimates:
## p
## 0.001308901
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.02
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.14
#########################################
##########Psychotic disorders############
#########################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios*100,1)
## [1] 86.4 6.6 6.9
KODAP_data_complete_Psychotic <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen"),]
length(KODAP_data_complete_Psychotic$Patient_ID)
## [1] 336
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Psychotic$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Psychotic$Patient_ID)
Observation
## [1] 331 4 1
round(Observation/length(KODAP_data_complete_Psychotic$Patient_ID)*100,1)
## [1] 98.5 1.2 0.3
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 42.102, df = 2, p-value = 7.207e-10
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 9.935806e-15
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 8.411055e-06
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 6.119362e-09
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.14000572 0.17919911 0.04286503
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 318.24, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003820372 0.032295397
## sample estimates:
## p
## 0.01190476
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.18
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.06 0.49
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 330.03, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0001553772 0.0190996535
## sample estimates:
## p
## 0.00297619
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.04
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.28
Subgroups of working-age adults
#Read prevalence estimates
Prevalence_estimates <- read_excel("Prevalence_estimates.xlsx")
Prevalence_estimates
## # A tibble: 17 × 6
## Diagnosis `1834y` `3549y` `5064y` `6574y` `75yplus`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Any mental disorder 35.8 28 26.4 19.6 19.6
## 2 Any mood disorder 15.1 10.3 7 5.9 5.9
## 3 Major Depressive Disorder 10 7.2 5.2 4.4 4.4
## 4 Dysthymia 2.1 1.7 1.3 1.6 1.6
## 5 Any anxiety disorder 18.1 16.2 15.3 11.1 11.1
## 6 Panic disorder/Agoraphobia 4.2 4.1 4.1 3.5 3.5
## 7 Social phobia 4.6 3.1 2.2 0.7 0.7
## 8 Specific phobias 12.3 9.5 10.9 8.4 8.4
## 9 GAD 3.3 2 2.3 1.3 1.3
## 10 OCD 7.2 3.6 2.2 1.1 1.1
## 11 PTSD 3.7 2.5 1 1.8 1.8
## 12 Any somatoform disorder 4.2 3.8 3.6 2.1 2.1
## 13 Somatization disorder 0.9 0.6 0.9 0.8 0.8
## 14 Pain disorder 4 3.8 3 1.6 1.6
## 15 Eating disorders 2.3 0.5 0.7 0.4 0.4
## 16 Substance use disorders 8.4 5.9 5.5 2.5 2.5
## 17 Psychotic disorders 4.2 2.2 2.5 1.3 1.3
##################
#####Analyses#####
##################
#Built Subset Datasets
KODAP_data_complete_s1 <- subset(KODAP_data_complete, Age_Stepped_2 %in% c(0,3,4))
KODAP_data_complete_s2 <- subset(KODAP_data_complete, Age_Stepped_2 %in% c(1,3,4))
KODAP_data_complete_s3 <- subset(KODAP_data_complete, Age_Stepped_2 %in% c(2,3,4))
#####################
#Any Mental Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.31 0.23 0.27 0.09 0.10
table(KODAP_data_complete$Age_Stepped_2)
##
## 0 1 2 3 4
## 7621 3144 2453 324 93
round(table(KODAP_data_complete$Age_Stepped_2)/length(KODAP_data_complete$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 55.9 23.1 18.0 2.4 0.7
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.62 0.18 0.19
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_s1$Age_Stepped))
Observation
## [1] 7621 324 93
round(Observation/length(KODAP_data_complete_s1$Patient_ID)*100, 1)
## [1] 94.8 4.0 1.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 3622.7, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.482197e-323
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.482197e-323
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 26.247684 14.515128 3.986448
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 6792.4, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03616484 0.04489775
## sample estimates:
## p
## 0.04030853
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.22
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574, 2)
## [1] 0.20 0.24
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 7668.4, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.009398471 0.014220596
## sample estimates:
## p
## 0.01157004
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.06
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.05 0.07
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.55 0.22 0.23
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_s2$Age_Stepped))
Observation
## [1] 3144 324 93
round(Observation/length(KODAP_data_complete_s2$Patient_ID)*100, 1)
## [1] 88.3 9.1 2.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 1651.8, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 8.079779e-94
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.351106e-269
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 10.828332 14.515128 3.986448
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 2381.3, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.08184183 0.10102412
## sample estimates:
## p
## 0.09098568
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.41
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574, 2)
## [1] 0.37 0.46
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 3196.8, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02124020 0.03204086
## sample estimates:
## p
## 0.02611626
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.11
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.09 0.14
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.58 0.20 0.21
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_s3$Age_Stepped))
Observation
## [1] 2453 324 93
round(Observation/length(KODAP_data_complete_s3$Patient_ID)*100, 1)
## [1] 85.5 11.3 3.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 921.22, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.25446e-218
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 7.903984e-38
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 9.47345e-175
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 8.448441 14.515128 3.986448
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1718.8, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.1016616 0.1251728
## sample estimates:
## p
## 0.112892
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.55
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574, 2)
## [1] 0.50 0.61
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 2508.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02636800 0.03972387
## sample estimates:
## p
## 0.03240418
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.15
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.12 0.19
#####################
#Any Mood Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.39 0.25 0.20 0.08 0.08
KODAP_data_complete_any_mood_disorder <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung"),]
table(KODAP_data_complete_any_mood_disorder$Age_Stepped_2)
##
## 0 1 2 3 4
## 4464 1877 1686 179 38
round(table(KODAP_data_complete_any_mood_disorder$Age_Stepped_2)/length(KODAP_data_complete_any_mood_disorder$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 54.1 22.8 20.5 2.2 0.5
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.70 0.15 0.15
KODAP_data_complete_any_mood_disorder <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung"),]
length(KODAP_data_complete_any_mood_disorder$Patient_ID)
## [1] 4681
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_mood_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_mood_disorder$Patient_ID)
Observation
## [1] 4464 179 38
round(Observation/length(KODAP_data_complete_any_mood_disorder$Patient_ID)*100,1)
## [1] 95.4 3.8 0.8
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 1457.2, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.400025e-131
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.946114e-273
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.36417267 0.25987270 0.05278597
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 3990.5, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03301440 0.04423693
## sample estimates:
## p
## 0.03823969
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.22 0.30
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 4528.3, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005830144 0.011245467
## sample estimates:
## p
## 0.008117924
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.04 0.07
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.60 0.20 0.21
KODAP_data_complete_any_mood_disorder <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung"),]
length(KODAP_data_complete_any_mood_disorder$Patient_ID)
## [1] 2094
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_mood_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_mood_disorder$Patient_ID)
Observation
## [1] 1877 179 38
round(Observation/length(KODAP_data_complete_any_mood_disorder$Patient_ID)*100,1)
## [1] 89.6 8.5 1.8
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 806.85, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.876927e-205
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.041346e-44
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 6.729488e-151
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.50235586 0.43342028 0.08803738
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1437.5, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.07402955 0.09848338
## sample estimates:
## p
## 0.08548233
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.43
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.38 0.50
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1942.8, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01304785 0.02508378
## sample estimates:
## p
## 0.01814709
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.09
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.06 0.12
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.55 0.22 0.23
KODAP_data_complete_any_mood_disorder <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung"),]
length(KODAP_data_complete_any_mood_disorder$Patient_ID)
## [1] 1903
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_mood_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_mood_disorder$Patient_ID)
Observation
## [1] 1686 179 38
round(Observation/length(KODAP_data_complete_any_mood_disorder$Patient_ID)*100,1)
## [1] 88.6 9.4 2.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 885.1, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.664017e-219
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 8.151518e-47
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.15282e-155
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.60616664 0.42901808 0.08714319
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1252.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.08150615 0.10828611
## sample estimates:
## p
## 0.09406201
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.43
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.37 0.49
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1752.1, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01436043 0.02759045
## sample estimates:
## p
## 0.01996847
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.09
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.06 0.12
###########################
#Major Depressive Disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.36 0.24 0.22 0.09 0.09
KODAP_data_complete_MDD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD2_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD3_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD4_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD5_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert"),]
table(KODAP_data_complete_MDD$Age_Stepped_2)
##
## 0 1 2 3 4
## 4050 1696 1515 163 36
round(table(KODAP_data_complete_MDD$Age_Stepped_2)/length(KODAP_data_complete_MDD$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 54.3 22.7 20.3 2.2 0.5
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.67 0.16 0.17
KODAP_data_complete_MDD <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert"),]
length(KODAP_data_complete_MDD$Patient_ID)
## [1] 4249
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_MDD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_MDD$Patient_ID)
Observation
## [1] 4050 163 36
round(Observation/length(KODAP_data_complete_MDD$Patient_ID)*100,1)
## [1] 95.3 3.8 0.8
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 1523.7, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.482197e-323
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.227732e-139
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 6.112485e-273
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.41523310 0.24029538 0.05077941
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 3620.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03288231 0.04469253
## sample estimates:
## p
## 0.03836197
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.24
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.21 0.28
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 4104.3, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.006027553 0.011842989
## sample estimates:
## p
## 0.008472582
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.04 0.07
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.58 0.20 0.21
KODAP_data_complete_MDD <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert"),]
length(KODAP_data_complete_MDD$Patient_ID)
## [1] 1895
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_MDD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_MDD$Patient_ID)
Observation
## [1] 1696 163 36
round(Observation/length(KODAP_data_complete_MDD$Patient_ID)*100,1)
## [1] 89.5 8.6 1.9
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 789.29, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.244867e-200
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.355558e-44
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.743262e-142
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.54048719 0.41981902 0.08871648
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1297.4, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.07396834 0.09977324
## sample estimates:
## p
## 0.08601583
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.42
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.36 0.49
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1751.8, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01353163 0.02649171
## sample estimates:
## p
## 0.01899736
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.09
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.06 0.12
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.55 0.22 0.23
KODAP_data_complete_MDD <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert"),]
length(KODAP_data_complete_MDD$Patient_ID)
## [1] 1714
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_MDD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_MDD$Patient_ID)
Observation
## [1] 1515 163 36
round(Observation/length(KODAP_data_complete_MDD$Patient_ID)*100,1)
## [1] 88.4 9.5 2.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 791.75, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 6.137925e-196
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.023715e-41
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.627408e-138
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.60522031 0.43281648 0.09146312
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1122.4, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.08183082 0.11021635
## sample estimates:
## p
## 0.09509918
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.43
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.37 0.50
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1571.1, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01496409 0.02927602
## sample estimates:
## p
## 0.0210035
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.09
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.07 0.13
###########################
#Dysthymia#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.30 0.23 0.21 0.12 0.13
KODAP_data_complete_Dysthymia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD2_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD3_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD4_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD5_pre_clean %in% c("F34.1", "F34.10"),]
table(KODAP_data_complete_Dysthymia$Age_Stepped_2)
##
## 0 1 2 3 4
## 508 224 203 22 1
round(table(KODAP_data_complete_Dysthymia$Age_Stepped_2)/length(KODAP_data_complete_Dysthymia$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 53.0 23.4 21.2 2.3 0.1
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.54 0.22 0.23
KODAP_data_complete_Dysthymia <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_s1$ICD2_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_s1$ICD3_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_s1$ICD4_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_s1$ICD5_pre_clean %in% c("F34.1", "F34.10"),]
length(KODAP_data_complete_Dysthymia$Patient_ID)
## [1] 531
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Dysthymia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Dysthymia$Patient_ID)
Observation
## [1] 508 22 1
round(Observation/length(KODAP_data_complete_Dysthymia$Patient_ID)*100,1)
## [1] 95.7 4.1 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 367.05, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.008176e-102
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.927829e-31
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.032302e-59
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.7597575 0.1856730 0.0080752
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 444.81, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02676267 0.06304503
## sample estimates:
## p
## 0.04143126
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.19
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.12 0.28
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 525.02, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0000983132 0.0121389098
## sample estimates:
## p
## 0.001883239
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.01
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.05
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.47 0.26 0.27
KODAP_data_complete_Dysthymia <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_s2$ICD2_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_s2$ICD3_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_s2$ICD4_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_s2$ICD5_pre_clean %in% c("F34.1", "F34.10"),]
length(KODAP_data_complete_Dysthymia$Patient_ID)
## [1] 247
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Dysthymia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Dysthymia$Patient_ID)
Observation
## [1] 224 22 1
round(Observation/length(KODAP_data_complete_Dysthymia$Patient_ID)*100,1)
## [1] 90.7 8.9 0.4
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 189.42, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 6.385702e-47
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.240164e-10
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.036754e-31
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.91423590 0.34614774 0.01505449
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 165.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.05791464 0.13350995
## sample estimates:
## p
## 0.08906883
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.35
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.23 0.52
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 241.04, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0002113729 0.0258703016
## sample estimates:
## p
## 0.004048583
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.02
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.0 0.1
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.46 0.27 0.28
KODAP_data_complete_Dysthymia <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_s3$ICD2_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_s3$ICD3_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_s3$ICD4_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_s3$ICD5_pre_clean %in% c("F34.1", "F34.10"),]
length(KODAP_data_complete_Dysthymia$Patient_ID)
## [1] 226
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Dysthymia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Dysthymia$Patient_ID)
Observation
## [1] 203 22 1
round(Observation/length(KODAP_data_complete_Dysthymia$Patient_ID)*100,1)
## [1] 89.8 9.7 0.4
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 180.87, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 4.775104e-44
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.603655e-09
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 6.64903e-30
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.9644403 0.3668026 0.0159528
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 144.96, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0633699 0.1455325
## sample estimates:
## p
## 0.09734513
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.37
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.24 0.55
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 220.04, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0002310174 0.0282316966
## sample estimates:
## p
## 0.004424779
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.02
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.0 0.1
###########################
#Any anxiety disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.29 0.24 0.28 0.10 0.10
KODAP_data_complete_any_anx_disorder <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen"),]
table(KODAP_data_complete_any_anx_disorder$Age_Stepped_2)
##
## 0 1 2 3 4
## 2725 929 664 106 29
round(table(KODAP_data_complete_any_anx_disorder$Age_Stepped_2)/length(KODAP_data_complete_any_anx_disorder$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 61.2 20.9 14.9 2.4 0.7
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.60 0.20 0.21
KODAP_data_complete_any_anx_disorder <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen"),]
length(KODAP_data_complete_any_anx_disorder$Patient_ID)
## [1] 2860
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_anx_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_anx_disorder$Patient_ID)
Observation
## [1] 2725 106 29
round(Observation/length(KODAP_data_complete_any_anx_disorder$Patient_ID)*100,1)
## [1] 95.3 3.7 1.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 1512, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 9.249153e-142
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.89704e-234
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.59656533 0.18798327 0.04920833
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 2449.9, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03057815 0.04482088
## sample estimates:
## p
## 0.03706294
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.19
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.16 0.23
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 2743.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.006925647 0.014729790
## sample estimates:
## p
## 0.01013986
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.07
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.55 0.22 0.23
KODAP_data_complete_any_anx_disorder <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen"),]
length(KODAP_data_complete_any_anx_disorder$Patient_ID)
## [1] 1064
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_anx_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_anx_disorder$Patient_ID)
Observation
## [1] 929 106 29
round(Observation/length(KODAP_data_complete_any_anx_disorder$Patient_ID)*100,1)
## [1] 87.3 10.0 2.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 454.82, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 5.933046e-112
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 6.070823e-24
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.89698e-78
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.5791805 0.4556972 0.1192878
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 680.64, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.08261257 0.11959103
## sample estimates:
## p
## 0.09962406
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.46
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.38 0.55
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 949.27, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01865566 0.03941759
## sample estimates:
## p
## 0.02725564
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.12
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.08 0.17
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.59 0.20 0.21
KODAP_data_complete_any_anx_disorder <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen"),]
length(KODAP_data_complete_any_anx_disorder$Patient_ID)
## [1] 799
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_anx_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_anx_disorder$Patient_ID)
Observation
## [1] 664 106 29
round(Observation/length(KODAP_data_complete_any_anx_disorder$Patient_ID)*100,1)
## [1] 83.1 13.3 3.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 213.78, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.280559e-48
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.361843e-06
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.612686e-45
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.4125144 0.6590868 0.1725290
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 429.78, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.1103173 0.1586226
## sample estimates:
## p
## 0.1326658
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.66
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.55 0.79
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 685.36, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02487130 0.05236749
## sample estimates:
## p
## 0.03629537
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.17
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.12 0.25
###########################
#Panic Disorder/Agoraphobia#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.25 0.23 0.28 0.11 0.12
KODAP_data_complete_PanicAgora <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung"),]
table(KODAP_data_complete_PanicAgora$Age_Stepped_2)
##
## 0 1 2 3 4
## 731 370 299 47 9
round(table(KODAP_data_complete_PanicAgora$Age_Stepped_2)/length(KODAP_data_complete_PanicAgora$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 50.2 25.4 20.5 3.2 0.6
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.52 0.23 0.24
KODAP_data_complete_PanicAgora <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung"),]
length(KODAP_data_complete_PanicAgora$Patient_ID)
## [1] 787
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PanicAgora$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PanicAgora$Patient_ID)
Observation
## [1] 731 47 9
round(Observation/length(KODAP_data_complete_PanicAgora$Patient_ID)*100,1)
## [1] 92.9 6.0 1.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 527.79, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.347813e-138
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.350377e-39
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 7.678958e-80
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.78164136 0.25516409 0.04675107
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 608.47, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.04465484 0.07922572
## sample estimates:
## p
## 0.05972046
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.19 0.34
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 749.46, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005591072 0.022412707
## sample estimates:
## p
## 0.01143583
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.02 0.09
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.50 0.25 0.26
KODAP_data_complete_PanicAgora <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung"),]
length(KODAP_data_complete_PanicAgora$Patient_ID)
## [1] 426
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PanicAgora$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PanicAgora$Patient_ID)
Observation
## [1] 370 47 9
round(Observation/length(KODAP_data_complete_PanicAgora$Patient_ID)*100,1)
## [1] 86.9 11.0 2.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 241, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 4.383763e-58
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 7.7275e-12
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 7.870622e-41
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.74360092 0.44959501 0.08237462
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 257.19, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0829624 0.1449315
## sample estimates:
## p
## 0.1103286
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.45
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.34 0.59
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 388.85, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01034477 0.04116685
## sample estimates:
## p
## 0.02112676
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.08
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.04 0.16
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.55 0.22 0.23
KODAP_data_complete_PanicAgora <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung"),]
length(KODAP_data_complete_PanicAgora$Patient_ID)
## [1] 355
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PanicAgora$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PanicAgora$Patient_ID)
Observation
## [1] 299 47 9
round(Observation/length(KODAP_data_complete_PanicAgora$Patient_ID)*100,1)
## [1] 84.2 13.2 2.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 133.34, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.252067e-31
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 8.755743e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 9.071155e-28
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.5356883 0.5996379 0.1098654
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 190.42, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.09980566 0.17316442
## sample estimates:
## p
## 0.1323944
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.6
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.45 0.78
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 318.02, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0124220 0.0492759
## sample estimates:
## p
## 0.02535211
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.11
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.05 0.21
###########################
#Social phobia#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.43 0.27 0.23 0.03 0.04
KODAP_data_complete_socialphobia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.1 Soziale Phobie"),]
table(KODAP_data_complete_socialphobia$Age_Stepped_2)
##
## 0 1 2 3 4
## 1407 295 128 16 4
round(table(KODAP_data_complete_socialphobia$Age_Stepped_2)/length(KODAP_data_complete_socialphobia$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 76.1 15.9 6.9 0.9 0.2
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.86 0.07 0.07
KODAP_data_complete_socialphobia <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F40.1 Soziale Phobie"),]
length(KODAP_data_complete_socialphobia$Patient_ID)
## [1] 1427
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_socialphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_socialphobia$Patient_ID)
Observation
## [1] 1407 16 4
round(Observation/length(KODAP_data_complete_socialphobia$Patient_ID)*100,1)
## [1] 98.6 1.1 0.3
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 195.58, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 7.003197e-67
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 6.415478e-26
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.729888e-40
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.15129299 0.15970153 0.03820115
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1361.8, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.006646199 0.018566480
## sample estimates:
## p
## 0.01121233
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.16
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.09 0.26
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1409.1, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0008983203 0.0076840834
## sample estimates:
## p
## 0.002803083
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.04
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.10
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.79 0.10 0.11
KODAP_data_complete_socialphobia <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F40.1 Soziale Phobie"),]
length(KODAP_data_complete_socialphobia$Patient_ID)
## [1] 315
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_socialphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_socialphobia$Patient_ID)
Observation
## [1] 295 16 4
round(Observation/length(KODAP_data_complete_socialphobia$Patient_ID)*100,1)
## [1] 93.7 5.1 1.3
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 43.267, df = 2, p-value = 4.025e-10
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.120926e-12
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.004490586
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.774582e-10
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1860866 0.4936742 0.1180885
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 252.46, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03028244 0.08281635
## sample estimates:
## p
## 0.05079365
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.49
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.29 0.80
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 297.26, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004075547 0.034417169
## sample estimates:
## p
## 0.01269841
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.12
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.04 0.32
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.77 0.11 0.12
KODAP_data_complete_socialphobia <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F40.1 Soziale Phobie"),]
length(KODAP_data_complete_socialphobia$Patient_ID)
## [1] 148
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_socialphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_socialphobia$Patient_ID)
Observation
## [1] 128 16 4
round(Observation/length(KODAP_data_complete_socialphobia$Patient_ID)*100,1)
## [1] 86.5 10.8 2.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 12.64, df = 2, p-value = 0.0018
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0.01035804
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.692998
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.0003292119
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1302657 0.9415832 0.2252299
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 89.358, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.06500968 0.17233195
## sample estimates:
## p
## 0.1081081
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.94
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.57 1.50
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 130.55, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.008692983 0.072068030
## sample estimates:
## p
## 0.02702703
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.23
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.07 0.60
###########################
#Specific phobias#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.29 0.21 0.29 0.11 0.11
KODAP_data_complete_specificphobia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.2 Spezifische Phobie"),]
table(KODAP_data_complete_specificphobia$Age_Stepped_2)
##
## 0 1 2 3 4
## 407 154 117 22 3
round(table(KODAP_data_complete_specificphobia$Age_Stepped_2)/length(KODAP_data_complete_specificphobia$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 57.9 21.9 16.6 3.1 0.4
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.57 0.21 0.22
KODAP_data_complete_specificphobia <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F40.2 Spezifische Phobie"),]
length(KODAP_data_complete_specificphobia$Patient_ID)
## [1] 432
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_specificphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_specificphobia$Patient_ID)
Observation
## [1] 407 22 3
round(Observation/length(KODAP_data_complete_specificphobia$Patient_ID)*100,1)
## [1] 94.2 5.1 0.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 245.39, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 6.210734e-68
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.918618e-20
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 4.551319e-41
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.65100426 0.24257153 0.03164942
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 346.69, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03293848 0.07726170
## sample estimates:
## p
## 0.05092593
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.24
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.16 0.37
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 418.11, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.001795201 0.021904551
## sample estimates:
## p
## 0.006944444
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.03
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.10
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.49 0.25 0.26
KODAP_data_complete_specificphobia <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F40.2 Spezifische Phobie"),]
length(KODAP_data_complete_specificphobia$Patient_ID)
## [1] 179
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_specificphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_specificphobia$Patient_ID)
Observation
## [1] 154 22 3
round(Observation/length(KODAP_data_complete_specificphobia$Patient_ID)*100,1)
## [1] 86.0 12.3 1.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 102.78, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 7.562553e-25
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.000125186
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.342115e-19
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.75814235 0.49222397 0.06422271
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 100.31, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.08030065 0.18225298
## sample estimates:
## p
## 0.122905
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.49
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.32 0.73
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 165.27, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004338373 0.052111880
## sample estimates:
## p
## 0.01675978
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.06
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.02 0.20
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.57 0.21 0.22
KODAP_data_complete_specificphobia <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F40.2 Spezifische Phobie"),]
length(KODAP_data_complete_specificphobia$Patient_ID)
## [1] 142
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_specificphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_specificphobia$Patient_ID)
Observation
## [1] 117 22 3
round(Observation/length(KODAP_data_complete_specificphobia$Patient_ID)*100,1)
## [1] 82.4 15.5 2.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 42.692, df = 2, p-value = 5.366e-10
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.183246e-09
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.3660296
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 4.056432e-11
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.43633485 0.74316156 0.09696369
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 66.261, df = 1, p-value = 3.951e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.1016958 0.2273905
## sample estimates:
## p
## 0.1549296
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.74
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.49 1.09
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 128.35, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005472072 0.065275438
## sample estimates:
## p
## 0.02112676
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.1
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.30
###########################
#Generalized Anxiety Disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.36 0.20 0.28 0.08 0.08
KODAP_data_complete_GAD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F41.1 Generalisierte Angststörung"),]
table(KODAP_data_complete_GAD$Age_Stepped_2)
##
## 0 1 2 3 4
## 254 147 125 20 6
round(table(KODAP_data_complete_GAD$Age_Stepped_2)/length(KODAP_data_complete_GAD$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 46.0 26.6 22.6 3.6 1.1
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.70 0.15 0.15
KODAP_data_complete_GAD <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F41.1 Generalisierte Angststörung"),]
length(KODAP_data_complete_GAD$Patient_ID)
## [1] 280
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_GAD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_GAD$Patient_ID)
Observation
## [1] 254 20 6
round(Observation/length(KODAP_data_complete_GAD$Patient_ID)*100,1)
## [1] 90.7 7.1 2.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 60.904, df = 2, p-value = 5.955e-14
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.331386e-16
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.0004063366
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 4.57727e-13
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.3008649 0.4826548 0.1385432
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 204, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0452875 0.1098397
## sample estimates:
## p
## 0.07142857
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.48
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.31 0.74
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 254.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.008740337 0.048335768
## sample estimates:
## p
## 0.02142857
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.14
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.06 0.31
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.57 0.21 0.22
KODAP_data_complete_GAD <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F41.1 Generalisierte Angststörung"),]
length(KODAP_data_complete_GAD$Patient_ID)
## [1] 173
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_GAD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_GAD$Patient_ID)
Observation
## [1] 147 20 6
round(Observation/length(KODAP_data_complete_GAD$Patient_ID)*100,1)
## [1] 85.0 11.6 3.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 59.559, df = 2, p-value = 1.166e-13
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 7.14875e-15
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.004372577
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.60061e-11
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.5015559 0.5446321 0.1563334
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 100.72, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.07376618 0.17513438
## sample estimates:
## p
## 0.1156069
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.54
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.35 0.83
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 147.98, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01417609 0.07738998
## sample estimates:
## p
## 0.03468208
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.16
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.06 0.35
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.65 0.17 0.18
KODAP_data_complete_GAD <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F41.1 Generalisierte Angststörung"),]
length(KODAP_data_complete_GAD$Patient_ID)
## [1] 151
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_GAD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_GAD$Patient_ID)
Observation
## [1] 125 20 6
round(Observation/length(KODAP_data_complete_GAD$Patient_ID)*100,1)
## [1] 82.8 13.2 4.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 25.563, df = 2, p-value = 2.813e-06
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 4.065834e-06
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.7057972
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.094089e-06
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.2790750 0.7677927 0.2203903
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 80.132, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0847233 0.1995018
## sample estimates:
## p
## 0.1324503
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.77
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.49 1.16
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 126.12, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01625461 0.08830168
## sample estimates:
## p
## 0.0397351
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.22
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.09 0.49
###########################
#Obsessive Compulsive Disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.50 0.24 0.18 0.04 0.04
KODAP_data_complete_OCD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F42.X Zwangsstörung"),]
table(KODAP_data_complete_OCD$Age_Stepped_2)
##
## 0 1 2 3 4
## 534 182 62 11 2
round(table(KODAP_data_complete_OCD$Age_Stepped_2)/length(KODAP_data_complete_OCD$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 67.5 23.0 7.8 1.4 0.3
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.86 0.07 0.07
KODAP_data_complete_OCD <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F42.X Zwangsstörung"),]
length(KODAP_data_complete_OCD$Patient_ID)
## [1] 547
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_OCD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_OCD$Patient_ID)
Observation
## [1] 534 11 2
round(Observation/length(KODAP_data_complete_OCD$Patient_ID)*100,1)
## [1] 97.6 2.0 0.4
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 65.297, df = 2, p-value = 6.622e-15
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.530773e-21
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.686373e-07
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.145261e-15
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.14055714 0.28546037 0.04966043
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 501.97, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01060965 0.03680152
## sample estimates:
## p
## 0.02010969
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.29
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.15 0.52
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 537.05, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0006335564 0.0146333230
## sample estimates:
## p
## 0.003656307
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.20
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.73 0.13 0.14
KODAP_data_complete_OCD <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F42.X Zwangsstörung"),]
length(KODAP_data_complete_OCD$Patient_ID)
## [1] 195
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_OCD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_OCD$Patient_ID)
Observation
## [1] 182 11 2
round(Observation/length(KODAP_data_complete_OCD$Patient_ID)*100,1)
## [1] 93.3 5.6 1.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 41.064, df = 2, p-value = 1.211e-09
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 4.902649e-12
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.003795649
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.130132e-09
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.2699121 0.4352785 0.0757237
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 151.71, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02993022 0.10132864
## sample estimates:
## p
## 0.05641026
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.44
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.23 0.78
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 185.13, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00177848 0.04048321
## sample estimates:
## p
## 0.01025641
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.08
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.30
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.67 0.16 0.17
KODAP_data_complete_OCD <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F42.X Zwangsstörung"),]
length(KODAP_data_complete_OCD$Patient_ID)
## [1] 75
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_OCD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_OCD$Patient_ID)
Observation
## [1] 62 11 2
round(Observation/length(KODAP_data_complete_OCD$Patient_ID)*100,1)
## [1] 82.7 14.7 2.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 11.431, df = 2, p-value = 0.003294
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0.01295206
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.625811
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.000800487
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.2253050 0.9219741 0.1603922
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 36.053, df = 1, p-value = 1.92e-09
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.07896563 0.25153073
## sample estimates:
## p
## 0.1466667
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.92
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.50 1.58
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 65.333, df = 1, p-value = 6.324e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004632317 0.101754797
## sample estimates:
## p
## 0.02666667
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.16
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.61
###########################
#Post Traumatic Stress Disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.40 0.25 0.12 0.11 0.11
KODAP_data_complete_PTSD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung"),]
table(KODAP_data_complete_PTSD$Age_Stepped_2)
##
## 0 1 2 3 4
## 628 244 180 13 2
round(table(KODAP_data_complete_PTSD$Age_Stepped_2)/length(KODAP_data_complete_PTSD$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 58.9 22.9 16.9 1.2 0.2
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.65 0.17 0.18
KODAP_data_complete_PTSD <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung"),]
length(KODAP_data_complete_PTSD$Patient_ID)
## [1] 643
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PTSD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PTSD$Patient_ID)
Observation
## [1] 628 13 2
round(Observation/length(KODAP_data_complete_PTSD$Patient_ID)*100,1)
## [1] 97.7 2.0 0.3
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 300.67, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 4.084108e-94
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.422531e-34
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 9.524682e-51
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.50015662 0.11849146 0.01744219
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 590.13, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01127810 0.03524888
## sample estimates:
## p
## 0.02021773
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.12
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.07 0.21
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 633.04, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0005389344 0.0124629319
## sample estimates:
## p
## 0.00311042
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.02
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.07
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.54 0.22 0.23
KODAP_data_complete_PTSD <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung"),]
length(KODAP_data_complete_PTSD$Patient_ID)
## [1] 259
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PTSD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PTSD$Patient_ID)
Observation
## [1] 244 13 2
round(Observation/length(KODAP_data_complete_PTSD$Patient_ID)*100,1)
## [1] 94.2 5.0 0.8
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 169.17, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.73753e-46
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.856052e-14
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.368796e-26
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.74262349 0.22345344 0.03289281
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 207.81, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02812696 0.08632672
## sample estimates:
## p
## 0.05019305
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.22
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.13 0.38
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 249.1, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.001338641 0.030641781
## sample estimates:
## p
## 0.007722008
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.03
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.13
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.37 0.31 0.32
KODAP_data_complete_PTSD <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung"),]
length(KODAP_data_complete_PTSD$Patient_ID)
## [1] 195
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PTSD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PTSD$Patient_ID)
Observation
## [1] 180 13 2
round(Observation/length(KODAP_data_complete_PTSD$Patient_ID)*100,1)
## [1] 92.3 6.7 1.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 262.45, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 7.045117e-60
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.594187e-16
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.13172e-29
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 2.52554367 0.21488036 0.03163084
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 144.74, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03745323 0.11380404
## sample estimates:
## p
## 0.06666667
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.21
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.12 0.37
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 185.13, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00177848 0.04048321
## sample estimates:
## p
## 0.01025641
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.03
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.12
###########################
#Any somatoform disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.30 0.25 0.29 0.08 0.08
KODAP_data_complete_Somatoform <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F45.X Somatoforme Störungen"),]
table(KODAP_data_complete_Somatoform$Age_Stepped_2)
##
## 0 1 2 3 4
## 400 262 347 48 17
round(table(KODAP_data_complete_Somatoform$Age_Stepped_2)/length(KODAP_data_complete_Somatoform$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 37.2 24.4 32.3 4.5 1.6
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.64 0.17 0.18
KODAP_data_complete_any_somatoform_disorder <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F45.X Somatoforme Störungen"),]
length(KODAP_data_complete_any_somatoform_disorder$Patient_ID)
## [1] 465
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_somatoform_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_somatoform_disorder$Patient_ID)
Observation
## [1] 400 48 17
round(Observation/length(KODAP_data_complete_any_somatoform_disorder$Patient_ID)*100,1)
## [1] 86.0 10.3 3.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 100.59, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 7.947645e-25
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 8.641975e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 6.861552e-21
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.3340877 0.5943375 0.2014040
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 291.23, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.07780415 0.13539946
## sample estimates:
## p
## 0.1032258
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.59
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.45 0.78
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 397.63, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02211704 0.05906098
## sample estimates:
## p
## 0.03655914
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.2
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.12 0.33
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.61 0.19 0.20
KODAP_data_complete_any_somatoform_disorder <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F45.X Somatoforme Störungen"),]
length(KODAP_data_complete_any_somatoform_disorder$Patient_ID)
## [1] 327
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_somatoform_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_somatoform_disorder$Patient_ID)
Observation
## [1] 262 48 17
round(Observation/length(KODAP_data_complete_any_somatoform_disorder$Patient_ID)*100,1)
## [1] 80.1 14.7 5.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 60.719, df = 2, p-value = 6.531e-14
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.110156e-13
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.1059443
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.011474e-14
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.3237986 0.7604814 0.2577054
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 161.77, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.1111872 0.1909164
## sample estimates:
## p
## 0.146789
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.76
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.58 0.99
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 260.75, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03152128 0.08350049
## sample estimates:
## p
## 0.05198777
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.16 0.41
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.64 0.18 0.18
KODAP_data_complete_any_somatoform_disorder <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F45.X Somatoforme Störungen"),]
length(KODAP_data_complete_any_somatoform_disorder$Patient_ID)
## [1] 412
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_somatoform_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_somatoform_disorder$Patient_ID)
Observation
## [1] 347 48 17
round(Observation/length(KODAP_data_complete_any_somatoform_disorder$Patient_ID)*100,1)
## [1] 84.2 11.7 4.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 80.254, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.060843e-19
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.003524904
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.518411e-17
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.3160686 0.6617851 0.2242601
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 240.84, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.08794403 0.15242546
## sample estimates:
## p
## 0.1165049
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.66
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.50 0.87
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 344.97, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02497916 0.06654107
## sample estimates:
## p
## 0.04126214
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.22
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.14 0.36
###########################
#Somatization disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.27 0.17 0.31 0.13 0.13
KODAP_data_complete_Somatization <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD2_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD3_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD4_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD5_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10"),]
table(KODAP_data_complete_Somatization$Age_Stepped_2)
##
## 0 1 2 3 4
## 105 42 56 7 1
round(table(KODAP_data_complete_Somatization$Age_Stepped_2)/length(KODAP_data_complete_Somatization$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 49.8 19.9 26.5 3.3 0.5
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.51 0.24 0.25
KODAP_data_complete_Somatization <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_s1$ICD2_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_s1$ICD3_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_s1$ICD4_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_s1$ICD5_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10"),]
length(KODAP_data_complete_Somatization$Patient_ID)
## [1] 113
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Somatization$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Somatization$Patient_ID)
Observation
## [1] 105 7 1
round(Observation/length(KODAP_data_complete_Somatization$Patient_ID)*100,1)
## [1] 92.9 6.2 0.9
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 81.944, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 4.954247e-22
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.294859e-06
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 8.540788e-13
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.83920676 0.25605270 0.03499924
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 84.991, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02741511 0.12796283
## sample estimates:
## p
## 0.0619469
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.11 0.53
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 107.08, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0004621214 0.0554818076
## sample estimates:
## p
## 0.008849558
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.03
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.22
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.39 0.30 0.31
KODAP_data_complete_Somatization <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_s2$ICD2_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_s2$ICD3_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_s2$ICD4_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_s2$ICD5_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10"),]
length(KODAP_data_complete_Somatization$Patient_ID)
## [1] 50
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Somatization$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Somatization$Patient_ID)
Observation
## [1] 42 7 1
round(Observation/length(KODAP_data_complete_Somatization$Patient_ID)*100,1)
## [1] 84 14 2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 44.139, df = 2, p-value = 2.602e-10
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.658583e-10
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.03871072
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 8.288633e-07
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 2.16183642 0.46826887 0.06400657
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 24.5, df = 1, p-value = 7.431e-07
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.06277009 0.27356376
## sample estimates:
## p
## 0.14
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.47
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.21 0.92
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 44.18, df = 1, p-value = 2.995e-11
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.001044888 0.120108120
## sample estimates:
## p
## 0.02
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.06
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.38
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.54 0.23 0.24
KODAP_data_complete_Somatization <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_s3$ICD2_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_s3$ICD3_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_s3$ICD4_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_s3$ICD5_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10"),]
length(KODAP_data_complete_Somatization$Patient_ID)
## [1] 64
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Somatization$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Somatization$Patient_ID)
Observation
## [1] 56 7 1
round(Observation/length(KODAP_data_complete_Somatization$Patient_ID)*100,1)
## [1] 87.5 10.9 1.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 30.466, df = 2, p-value = 2.424e-07
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 5.360789e-08
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.07319309
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.035337e-06
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.6251259 0.4846108 0.0662403
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 37.516, df = 1, p-value = 9.068e-10
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.04878566 0.21841190
## sample estimates:
## p
## 0.109375
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.48
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.22 0.97
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 58.141, df = 1, p-value = 2.44e-14
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0008161675 0.0954135903
## sample estimates:
## p
## 0.015625
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.0 0.4
###########################
#Pain disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.31 0.28 0.27 0.07 0.07
KODAP_data_complete_Pain <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD2_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD3_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD4_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD5_pre_clean %in% c("F45.4","F45.40", "F45.41"),]
table(KODAP_data_complete_Pain$Age_Stepped_2)
##
## 0 1 2 3 4
## 99 125 241 30 13
round(table(KODAP_data_complete_Pain$Age_Stepped_2)/length(KODAP_data_complete_Pain$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 19.5 24.6 47.4 5.9 2.6
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.69 0.15 0.16
KODAP_data_complete_Pain <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_s1$ICD2_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_s1$ICD3_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_s1$ICD4_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_s1$ICD5_pre_clean %in% c("F45.4","F45.40", "F45.41"),]
length(KODAP_data_complete_Pain$Patient_ID)
## [1] 142
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Pain$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Pain$Patient_ID)
Observation
## [1] 99 30 13
round(Observation/length(KODAP_data_complete_Pain$Patient_ID)*100,1)
## [1] 69.7 21.1 9.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 7.4268, df = 2, p-value = 0.02439
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.1351746
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.1097324
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0044328 1.4124871 0.5856443
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 46.204, df = 1, p-value = 1.065e-11
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.1491534 0.2893742
## sample estimates:
## p
## 0.2112676
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 1.41
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 1.00 1.93
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 93.134, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.05163224 0.15451986
## sample estimates:
## p
## 0.0915493
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.59
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.33 0.99
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.67 0.16 0.17
KODAP_data_complete_Pain <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_s2$ICD2_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_s2$ICD3_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_s2$ICD4_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_s2$ICD5_pre_clean %in% c("F45.4","F45.40", "F45.41"),]
length(KODAP_data_complete_Pain$Patient_ID)
## [1] 168
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Pain$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Pain$Patient_ID)
Observation
## [1] 125 30 13
round(Observation/length(KODAP_data_complete_Pain$Patient_ID)*100,1)
## [1] 74.4 17.9 7.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 10.157, df = 2, p-value = 0.00623
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0.1207022
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.594905
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.00269835
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1137879 1.1001194 0.4561306
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 68.149, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.1255001 0.2467382
## sample estimates:
## p
## 0.1785714
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 1.1
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.77 1.52
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 118.34, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.04354488 0.13145155
## sample estimates:
## p
## 0.07738095
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.46
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.26 0.77
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.66 0.17 0.17
KODAP_data_complete_Pain <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_s3$ICD2_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_s3$ICD3_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_s3$ICD4_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_s3$ICD5_pre_clean %in% c("F45.4","F45.40", "F45.41"),]
length(KODAP_data_complete_Pain$Patient_ID)
## [1] 284
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Pain$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Pain$Patient_ID)
Observation
## [1] 241 30 13
round(Observation/length(KODAP_data_complete_Pain$Patient_ID)*100,1)
## [1] 84.9 10.6 4.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 48.214, df = 2, p-value = 3.391e-11
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.184466e-12
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.01537115
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.042024e-10
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.2850833 0.6360339 0.2637119
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 175.1, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.07351973 0.14878350
## sample estimates:
## p
## 0.1056338
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.64
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.44 0.90
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 232.57, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02563367 0.07888574
## sample estimates:
## p
## 0.04577465
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.15 0.45
###########################
#Eating disorders#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.57 0.12 0.20 0.05 0.06
KODAP_data_complete_Eating <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F50.X Essstörung"),]
table(KODAP_data_complete_Eating$Age_Stepped_2)
##
## 0 1 2 3
## 592 168 89 8
round(table(KODAP_data_complete_Eating$Age_Stepped_2)/length(KODAP_data_complete_Eating$Age_Stepped_2)*100, 1)
##
## 0 1 2 3
## 69.1 19.6 10.4 0.9
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.84 0.08 0.08
KODAP_data_complete_Eating <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F50.X Essstörung"),]
length(KODAP_data_complete_Eating$Patient_ID)
## [1] 600
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Eating$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Eating$Patient_ID)
Observation
## [1] 592 8
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_Eating$Patient_ID)*100,1)
## [1] 98.7 1.3 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 97.384, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 7.296144e-34
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.250234e-12
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.383093e-22
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1757212 0.1695813 0.0000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 566.48, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.006212746 0.027177067
## sample estimates:
## p
## 0.01333333
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.17
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.08 0.35
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 598, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.000000000 0.007930758
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.0 0.1
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.51 0.24 0.25
KODAP_data_complete_Eating <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F50.X Essstörung"),]
length(KODAP_data_complete_Eating$Patient_ID)
## [1] 176
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Eating$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Eating$Patient_ID)
Observation
## [1] 168 8
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_Eating$Patient_ID)*100,1)
## [1] 95.5 4.5 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 137.31, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 9.306154e-38
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.277145e-11
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 8.446139e-22
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.8557976 0.1914184 0.0000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 143.64, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02128851 0.09072927
## sample estimates:
## p
## 0.04545455
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.19
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.09 0.38
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 174.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.02662404
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.11
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.64 0.17 0.18
KODAP_data_complete_Eating <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F50.X Essstörung"),]
length(KODAP_data_complete_Eating$Patient_ID)
## [1] 97
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Eating$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Eating$Patient_ID)
Observation
## [1] 89 8
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_Eating$Patient_ID)*100,1)
## [1] 91.8 8.2 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 33.461, df = 2, p-value = 5.419e-08
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.289087e-09
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.04589785
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.866035e-08
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.4231861 0.4747262 0.0000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 65.979, df = 1, p-value = 4.557e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03885986 0.16071710
## sample estimates:
## p
## 0.08247423
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.47
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.22 0.93
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 95.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.04747222
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.26
###########################
#Substance use disorders#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.37 0.24 0.27 0.06 0.06
KODAP_data_complete_SubstanceUse <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen"),]
table(KODAP_data_complete_SubstanceUse$Age_Stepped_2)
##
## 0 1 2 3 4
## 400 217 131 15 1
round(table(KODAP_data_complete_SubstanceUse$Age_Stepped_2)/length(KODAP_data_complete_SubstanceUse$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 52.4 28.4 17.1 2.0 0.1
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.75 0.12 0.13
KODAP_data_complete_SubstanceUse <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen"),]
length(KODAP_data_complete_SubstanceUse$Patient_ID)
## [1] 416
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_SubstanceUse$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_SubstanceUse$Patient_ID)
Observation
## [1] 400 15 1
round(Observation/length(KODAP_data_complete_SubstanceUse$Patient_ID)*100,1)
## [1] 96.2 3.6 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 99.23, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.068019e-30
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 5.153776e-09
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.494718e-22
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.27682976 0.29863526 0.01904922
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 356.31, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02105849 0.06009847
## sample estimates:
## p
## 0.03605769
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.3
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.17 0.50
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 410.02, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0001254939 0.0154621692
## sample estimates:
## p
## 0.002403846
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.02
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.12
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.67 0.16 0.17
KODAP_data_complete_SubstanceUse <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen"),]
length(KODAP_data_complete_SubstanceUse$Patient_ID)
## [1] 233
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_SubstanceUse$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_SubstanceUse$Patient_ID)
Observation
## [1] 217 15 1
round(Observation/length(KODAP_data_complete_SubstanceUse$Patient_ID)*100,1)
## [1] 93.1 6.4 0.4
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 76.115, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.231021e-21
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.297435e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.881608e-17
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.39707901 0.39493620 0.02519202
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 175.12, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03775731 0.10606033
## sample estimates:
## p
## 0.06437768
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.39
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.23 0.65
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 227.04, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0002240757 0.0273980814
## sample estimates:
## p
## 0.004291845
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.03
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.16
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.70 0.15 0.16
KODAP_data_complete_SubstanceUse <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen"),]
length(KODAP_data_complete_SubstanceUse$Patient_ID)
## [1] 147
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_SubstanceUse$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_SubstanceUse$Patient_ID)
Observation
## [1] 131 15 1
round(Observation/length(KODAP_data_complete_SubstanceUse$Patient_ID)*100,1)
## [1] 89.1 10.2 0.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 31.234, df = 2, p-value = 1.651e-07
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 7.705711e-08
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.3932277
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.312169e-09
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.28182632 0.68472367 0.04367686
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 91.537, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.06019127 0.16552137
## sample estimates:
## p
## 0.1020408
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.68
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.40 1.11
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 141.06, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0003552053 0.0429952284
## sample estimates:
## p
## 0.006802721
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.04
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.28
###########################
#Psychotic disorders#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "5064y"])
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "75yplus"])
expected_ratio_1834 <- (census_amount_1834*prevalence_1834)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_3549 <- (census_amount_3549*prevalence_3549)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_5064 <- (census_amount_5064*prevalence_5064)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1834)+(census_amount_3549*prevalence_3549)+(census_amount_5064*prevalence_5064)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
round(c(expected_ratio_1834,expected_ratio_3549,expected_ratio_5064,expected_ratio_6574,expected_ratio_75plus), 2)
## [1] 0.40 0.19 0.27 0.07 0.07
KODAP_data_complete_Psychotic <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen"),]
table(KODAP_data_complete_Psychotic$Age_Stepped_2)
##
## 0 1 2 3 4
## 161 121 49 4 1
round(table(KODAP_data_complete_Psychotic$Age_Stepped_2)/length(KODAP_data_complete_Psychotic$Age_Stepped_2)*100, 1)
##
## 0 1 2 3 4
## 47.9 36.0 14.6 1.2 0.3
#18-34 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "5064y"])
prevalence_1864 <- prevalence_1834
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1834*prevalence_1864)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1834*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.75 0.12 0.13
KODAP_data_complete_Psychotic <- KODAP_data_complete_s1[KODAP_data_complete_s1$ICD1_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_s1$ICD2_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_s1$ICD3_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_s1$ICD4_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_s1$ICD5_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen"),]
length(KODAP_data_complete_Psychotic$Patient_ID)
## [1] 166
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Psychotic$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Psychotic$Patient_ID)
Observation
## [1] 161 4 1
round(Observation/length(KODAP_data_complete_Psychotic$Patient_ID)*100,1)
## [1] 97.0 2.4 0.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 44.222, df = 2, p-value = 2.496e-10
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.89182e-14
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.61255e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.338643e-08
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.30062692 0.19378954 0.04635511
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 148.49, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.007746952 0.064467251
## sample estimates:
## p
## 0.02409639
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.19
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.06 0.52
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 160.05, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0003145389 0.0381918572
## sample estimates:
## p
## 0.006024096
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.29
#35-49 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "5064y"])
prevalence_1864 <- prevalence_3549
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_3549*prevalence_1864)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_3549*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.59 0.20 0.21
KODAP_data_complete_Psychotic <- KODAP_data_complete_s2[KODAP_data_complete_s2$ICD1_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_s2$ICD2_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_s2$ICD3_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_s2$ICD4_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_s2$ICD5_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen"),]
length(KODAP_data_complete_Psychotic$Patient_ID)
## [1] 126
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Psychotic$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Psychotic$Patient_ID)
Observation
## [1] 121 4 1
round(Observation/length(KODAP_data_complete_Psychotic$Patient_ID)*100,1)
## [1] 96.0 3.2 0.8
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 71.905, df = 2, p-value = 2.433e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.042486e-21
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.22867e-07
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.955996e-11
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.63004042 0.15802099 0.03779915
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 108.64, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01021808 0.08420081
## sample estimates:
## p
## 0.03174603
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.16
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.05 0.42
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 120.07, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0004144261 0.0499367756
## sample estimates:
## p
## 0.007936508
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.04
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.24
#50-64 years
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "5064y"])
prevalence_1864 <- prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_5064*prevalence_1864)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_5064*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.67 0.16 0.17
KODAP_data_complete_Psychotic <- KODAP_data_complete_s3[KODAP_data_complete_s3$ICD1_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_s3$ICD2_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_s3$ICD3_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_s3$ICD4_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_s3$ICD5_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen"),]
length(KODAP_data_complete_Psychotic$Patient_ID)
## [1] 54
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Psychotic$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Psychotic$Patient_ID)
Observation
## [1] 49 4 1
round(Observation/length(KODAP_data_complete_Psychotic$Patient_ID)*100,1)
## [1] 90.7 7.4 1.9
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 14.684, df = 2, p-value = 0.0006476
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0.0001932065
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.2852669
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.002563779
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.3624838 0.4535607 0.1084933
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 37.5, df = 1, p-value = 9.141e-10
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02399672 0.18741913
## sample estimates:
## p
## 0.07407407
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.45
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.15 1.15
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 48.167, df = 1, p-value = 3.915e-12
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0009674283 0.1118384229
## sample estimates:
## p
## 0.01851852
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.11
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.66
Gender-specific analyses
#Only include female patients
KODAP_data_complete_female <- subset(KODAP_data_complete, Pat_Geschlecht == 2)
#Read prevalence estimates
Prevalence_estimates <- read_excel("Prevalence_estimates_female.xlsx")
Prevalence_estimates
## # A tibble: 17 × 6
## Diagnosis `1834y` `3549y` `5064y` `6574y` `75yplus`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Any mental disorder 41.8 34.9 31.6 24.4 24.4
## 2 Any mood disorder 20.7 14.8 7.8 8.4 8.4
## 3 Major Depressive Disorder 15.1 10.6 5.8 6.2 6.2
## 4 Dysthymia 2.4 2.4 1.4 2.3 2.3
## 5 Any anxiety disorder 26.5 21.8 21.4 14.9 14.9
## 6 Panic disorder/Agoraphobia 6.1 5.5 6 4.8 4.8
## 7 Social phobia 6.8 4.2 2.5 0.7 0.7
## 8 Specific phobias 19.9 13.8 16.7 11.3 11.3
## 9 GAD 4.7 2.3 2.8 2.1 2.1
## 10 OCD 7.4 4.2 2.2 2 2
## 11 PTSD 6.1 3.8 1.7 2.9 2.9
## 12 Any somatoform disorder 6.5 6.4 4.6 3 3
## 13 Somatization disorder 1.3 1.2 0.3 1.1 1.1
## 14 Pain disorder 6.4 6.3 4.5 2.5 2.5
## 15 Eating disorders 3.6 0.8 0.9 0.3 0.3
## 16 Substance use disorders 3.9 4.4 3 2.6 2.6
## 17 Psychotic disorders 5.6 2.6 2.4 1.6 1.6
##################
#####Analyses#####
##################
#####################
#Any Mental Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.78 0.10 0.12
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female$Patient_ID)
Observation
## [1] 8447 224 67
round(Observation/length(KODAP_data_complete_female$Patient_ID)*100, 1)
## [1] 96.7 2.6 0.8
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 1751.8, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.482197e-323
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.801795e-162
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.23451433 0.25661306 0.06551135
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 7863.1, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02247042 0.02922398
## sample estimates:
## p
## 0.02563516
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574, 2)
## [1] 0.22 0.29
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 8470.1, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005992240 0.009789213
## sample estimates:
## p
## 0.007667659
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.05 0.08
#####################
#Any Mood Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.80 0.09 0.11
KODAP_data_complete_female_any_mood_disorder <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_female$ICD5_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung"),]
length(KODAP_data_complete_female_any_mood_disorder$Patient_ID)
## [1] 5241
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_any_mood_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_any_mood_disorder$Patient_ID)
Observation
## [1] 5093 121 27
round(Observation/length(KODAP_data_complete_female_any_mood_disorder$Patient_ID)*100,1)
## [1] 97.2 2.3 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 946.48, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 6.439132e-296
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 5.306085e-88
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.910448e-207
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.20856048 0.25588457 0.04873416
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 4766.3, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01926997 0.02761936
## sample estimates:
## p
## 0.0230872
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.21 0.31
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 5131.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003465327 0.007597990
## sample estimates:
## p
## 0.005151689
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.07
###########################
#Major Depressive Disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.80 0.09 0.11
KODAP_data_complete_female_MDD <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert")|
KODAP_data_complete_female$ICD5_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert"),]
length(KODAP_data_complete_female_MDD$Patient_ID)
## [1] 4773
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_MDD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_MDD$Patient_ID)
Observation
## [1] 4639 109 25
round(Observation/length(KODAP_data_complete_female_MDD$Patient_ID)*100,1)
## [1] 97.2 2.3 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 877.96, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 4.436099e-275
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.104863e-82
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.757643e-190
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.21199486 0.25037097 0.04901269
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 4345, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01887173 0.02758819
## sample estimates:
## p
## 0.02283679
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.25
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.21 0.30
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 4671.5, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003465793 0.007845503
## sample estimates:
## p
## 0.005237796
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.07
###########################
#########Dysthymia#########
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.68 0.15 0.17
KODAP_data_complete_female_Dysthymia <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_female$ICD2_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_female$ICD3_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_female$ICD4_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_female$ICD5_pre_clean %in% c("F34.1", "F34.10"),]
length(KODAP_data_complete_female_Dysthymia$Patient_ID)
## [1] 549
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_Dysthymia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_Dysthymia$Patient_ID)
Observation
## [1] 528 20 1
round(Observation/length(KODAP_data_complete_female_Dysthymia$Patient_ID)*100,1)
## [1] 96.2 3.6 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 198.83, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 4.743738e-60
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.54765e-16
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.266975e-42
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.40685683 0.25005007 0.01067107
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 470.06, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02298407 0.05668338
## sample estimates:
## p
## 0.03642987
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.25
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.16 0.39
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 543.02, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 9.508956e-05 1.174384e-02
## sample estimates:
## p
## 0.001821494
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.01
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.07
###########################
##Any anxiety disorder#####
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.79 0.10 0.11
KODAP_data_complete_female_any_anx_disorder <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_female$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen"),]
length(KODAP_data_complete_female_any_anx_disorder$Patient_ID)
## [1] 2874
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_any_anx_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_any_anx_disorder$Patient_ID)
Observation
## [1] 2784 69 21
round(Observation/length(KODAP_data_complete_female_any_anx_disorder$Patient_ID)*100,1)
## [1] 96.9 2.4 0.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 548.22, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.150625e-170
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.655144e-52
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.646734e-114
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.22253012 0.25109478 0.06522572
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 2602.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01886099 0.03046568
## sample estimates:
## p
## 0.02400835
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.25
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.20 0.32
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 2788.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004646579 0.011354394
## sample estimates:
## p
## 0.007306889
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.04 0.10
#################################
##Panic Disorder/Agoraphobia#####
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.75 0.11 0.13
KODAP_data_complete_female_PanicAgora <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_female$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung"),]
length(KODAP_data_complete_female_PanicAgora$Patient_ID)
## [1] 957
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_PanicAgora$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_PanicAgora$Patient_ID)
Observation
## [1] 923 29 5
round(Observation/length(KODAP_data_complete_female_PanicAgora$Patient_ID)*100,1)
## [1] 96.4 3.0 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 236.84, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 9.483517e-73
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 7.073749e-21
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.243387e-51
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.28493785 0.26385897 0.03882888
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 842.64, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02074943 0.04379001
## sample estimates:
## p
## 0.03030303
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.18 0.38
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 935.13, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.001925064 0.012895172
## sample estimates:
## p
## 0.00522466
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.04
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.10
#################################
##########Social phobia##########
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.94 0.03 0.03
KODAP_data_complete_female_socialphobia <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_female$ICD5_pre_recode %in% c("F40.1 Soziale Phobie"),]
length(KODAP_data_complete_female_socialphobia$Patient_ID)
## [1] 1105
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_socialphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_socialphobia$Patient_ID)
Observation
## [1] 1094 9 2
round(Observation/length(KODAP_data_complete_female_socialphobia$Patient_ID)*100,1)
## [1] 99.0 0.8 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 51.227, df = 2, p-value = 7.519e-12
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.541934e-17
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.878888e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 4.71703e-13
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.05439582 0.28981209 0.05496864
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1067.3, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003980008 0.015994121
## sample estimates:
## p
## 0.008144796
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.29
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.14 0.57
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1095, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.000313562 0.007272171
## sample estimates:
## p
## 0.001809955
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.22
#################################
##########Specific phobia##########
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.79 0.10 0.12
KODAP_data_complete_female_specificphobia <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_female$ICD5_pre_recode %in% c("F40.2 Spezifische Phobie"),]
length(KODAP_data_complete_female_specificphobia$Patient_ID)
## [1] 512
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_specificphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_specificphobia$Patient_ID)
Observation
## [1] 492 17 3
round(Observation/length(KODAP_data_complete_female_specificphobia$Patient_ID)*100,1)
## [1] 96.1 3.3 0.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 95.833, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.216676e-29
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 8.609206e-08
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.314941e-22
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.22351522 0.33598159 0.05060563
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 444.39, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02007705 0.05370694
## sample estimates:
## p
## 0.03320312
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.34
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.20 0.54
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 498.1, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.001514477 0.018511450
## sample estimates:
## p
## 0.005859375
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.16
################################################
##########Generalized Anxiety Disorder##########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.79 0.10 0.11
KODAP_data_complete_female_GAD <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_female$ICD5_pre_recode %in% c("F41.1 Generalisierte Angststörung"),]
length(KODAP_data_complete_female_GAD$Patient_ID)
## [1] 399
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_GAD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_GAD$Patient_ID)
Observation
## [1] 379 14 6
round(Observation/length(KODAP_data_complete_female_GAD$Patient_ID)*100,1)
## [1] 95.0 3.5 1.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 61.597, df = 2, p-value = 4.212e-14
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.65055e-18
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.592153e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.805281e-13
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1996566 0.3659621 0.1338660
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 343.11, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02007309 0.05956381
## sample estimates:
## p
## 0.03508772
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.37
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.21 0.62
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 373.42, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.006127367 0.034097737
## sample estimates:
## p
## 0.01503759
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.13
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.05 0.30
################################################
##########Obsessive compulsive disorders########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.85 0.07 0.08
KODAP_data_complete_female_OCD <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_female$ICD5_pre_recode %in% c("F42.X Zwangsstörung"),]
length(KODAP_data_complete_female_OCD$Patient_ID)
## [1] 478
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_OCD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_OCD$Patient_ID)
Observation
## [1] 469 7 2
round(Observation/length(KODAP_data_complete_female_OCD$Patient_ID)*100,1)
## [1] 98.1 1.5 0.4
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 67.693, df = 2, p-value = 1.998e-15
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 8.995839e-23
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 5.876961e-08
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.09016e-15
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.16023445 0.20606077 0.05025026
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 448.47, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0064319 0.0313004
## sample estimates:
## p
## 0.01464435
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.21
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.09 0.44
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 468.05, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0007250526 0.0167270175
## sample estimates:
## p
## 0.0041841
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.20
################################################
##########Post traumatic stress disorder########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.76 0.11 0.13
KODAP_data_complete_female_PTSD <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_female$ICD5_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung"),]
length(KODAP_data_complete_female_PTSD$Patient_ID)
## [1] 826
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_PTSD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_PTSD$Patient_ID)
Observation
## [1] 815 9 2
round(Observation/length(KODAP_data_complete_female_PTSD$Patient_ID)*100,1)
## [1] 98.7 1.1 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 233.05, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.619396e-79
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.667058e-29
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 8.731105e-46
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.29831656 0.09857881 0.01869744
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 788.44, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005326636 0.021361366
## sample estimates:
## p
## 0.01089588
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.1
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.05 0.19
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 816.03, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0004195024 0.0097159245
## sample estimates:
## p
## 0.002421308
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.02
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.08
################################################
##########Any somatoform Disorders##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.82 0.08 0.09
KODAP_data_complete_female_Somatoform <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_female$ICD5_pre_recode %in% c("F45.X Somatoforme Störungen"),]
length(KODAP_data_complete_female_Somatoform$Patient_ID)
## [1] 717
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_Somatoform$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_Somatoform$Patient_ID)
Observation
## [1] 668 38 11
round(Observation/length(KODAP_data_complete_female_Somatoform$Patient_ID)*100,1)
## [1] 93.2 5.3 1.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 64.208, df = 2, p-value = 1.141e-14
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.898274e-16
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.01463704
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 6.874491e-18
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1294049 0.6573448 0.1624102
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 571.27, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03826044 0.07270099
## sample estimates:
## p
## 0.05299861
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.66
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.47 0.90
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 671.74, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.008088178 0.028144685
## sample estimates:
## p
## 0.0153417
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.16
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.09 0.30
################################################
##########Somatization disorder##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.67 0.15 0.18
KODAP_data_complete_female_Somatization <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_female$ICD2_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_female$ICD3_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_female$ICD4_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_female$ICD5_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10"),]
length(KODAP_data_complete_female_Somatization$Patient_ID)
## [1] 138
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_Somatization$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_Somatization$Patient_ID)
Observation
## [1] 134 4
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_female_Somatization$Patient_ID)*100,1)
## [1] 97.1 2.9 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 58.174, df = 2, p-value = 2.332e-13
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.878195e-18
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 8.412681e-06
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 7.220013e-12
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.4583628 0.1883615 0.0000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 120.59, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.009325662 0.077119213
## sample estimates:
## p
## 0.02898551
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.19
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.06 0.50
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 136.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.03375451
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.19
################################################
##########Pain disorder##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.85 0.07 0.08
KODAP_data_complete_female_Pain <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_female$ICD2_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_female$ICD3_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_female$ICD4_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_female$ICD5_pre_clean %in% c("F45.4","F45.40", "F45.41"),]
length(KODAP_data_complete_female_Pain$Patient_ID)
## [1] 373
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_Pain$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_Pain$Patient_ID)
Observation
## [1] 336 28 9
round(Observation/length(KODAP_data_complete_female_Pain$Patient_ID)*100,1)
## [1] 90.1 7.5 2.4
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 16.713, df = 2, p-value = 0.0002349
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0.00929641
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.055383
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.367474e-05
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0629533 1.0686467 0.2931768
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 267.71, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.05133188 0.10789203
## sample estimates:
## p
## 0.07506702
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 1.07
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.73 1.54
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 335.97, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01182026 0.04693220
## sample estimates:
## p
## 0.02412869
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.29
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.14 0.57
################################################
##########Eating disorders##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.93 0.03 0.04
KODAP_data_complete_female_Eating <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_female$ICD5_pre_recode %in% c("F50.X Essstörung"),]
length(KODAP_data_complete_female_Eating$Patient_ID)
## [1] 760
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_Eating$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_Eating$Patient_ID)
Observation
## [1] 754 6
Observation[3] <- 0
Observation
## [1] 754 6 0
round(Observation/length(KODAP_data_complete_female_Eating$Patient_ID)*100,1)
## [1] 99.2 0.8 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 42.522, df = 2, p-value = 5.84e-10
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 6.40344e-15
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.0001407409
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 6.997406e-12
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0622881 0.2594979 0.0000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 734.22, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003213246 0.018006521
## sample estimates:
## p
## 0.007894737
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.11 0.59
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 758, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.000000000 0.006269615
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.18
#########################################
##########Substance-use disorders########
#########################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.78 0.10 0.12
KODAP_data_complete_female_SubstanceUse <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_female$ICD5_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen"),]
length(KODAP_data_complete_female_SubstanceUse$Patient_ID)
## [1] 322
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_SubstanceUse$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_SubstanceUse$Patient_ID)
Observation
## [1] 317 5
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_female_SubstanceUse$Patient_ID)*100,1)
## [1] 98.4 1.6 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 79.775, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.083161e-27
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.848148e-09
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 7.630713e-18
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.2650321 0.1520459 0.0000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 300.38, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005730545 0.037951171
## sample estimates:
## p
## 0.01552795
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.15
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.06 0.37
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 320, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.01469619
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.12
#########################################
##########Psychotic disorders############
#########################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "5064y"])
prevalence_1864 <- (female_amount_1834/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_1834+
(female_amount_3549/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_3549+
(female_amount_5064/sum(female_amount_1834,female_amount_3549, female_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (female_amount_1864*prevalence_1864)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (female_amount_6574*prevalence_6574)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (female_amount_75plus*prevalence_75plus)/((female_amount_1864*prevalence_1864)+(female_amount_6574*prevalence_6574)+(female_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.84 0.07 0.09
KODAP_data_complete_female_Psychotic <- KODAP_data_complete_female[KODAP_data_complete_female$ICD1_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_female$ICD2_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_female$ICD3_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_female$ICD4_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_female$ICD5_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen"),]
length(KODAP_data_complete_female_Psychotic$Patient_ID)
## [1] 153
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_female_Psychotic$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_female_Psychotic$Patient_ID)
Observation
## [1] 153
Observation[2] <- 0
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_female_Psychotic$Patient_ID)*100,1)
## [1] 100 0 0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 28.661, df = 2, p-value = 5.976e-07
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.940281e-11
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.562047e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 8.860853e-06
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.187324 0.000000 0.000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 151.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.03052722
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.00 0.42
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 151.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.03052722
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.36
#only include male patients
KODAP_data_complete_male <- subset(KODAP_data_complete, Pat_Geschlecht == 1)
#Read prevalence estimates
Prevalence_estimates <- read_excel("Prevalence_estimates_male.xlsx")
Prevalence_estimates
## # A tibble: 17 × 6
## Diagnosis `1834y` `3549y` `5064y` `6574y` `75yplus`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Any mental disorder 30 21.2 21.2 14.3 14.3
## 2 Any mood disorder 9.6 5.9 6.3 3 3
## 3 Major Depressive Disorder 4.9 3.9 4.6 2.3 2.3
## 4 Dysthymia 1.9 0.9 1.2 0.8 0.8
## 5 Any anxiety disorder 9.9 10.7 9.2 6.7 6.7
## 6 Panic disorder/Agoraphobia 2.2 2.7 2.3 2 2
## 7 Social phobia 2.5 2.1 1.8 0.7 0.7
## 8 Specific phobias 4.9 5.3 5.1 5.1 5.1
## 9 GAD 1.9 1.7 1.8 0.4 0.4
## 10 OCD 7.1 3 2.1 0.2 0.2
## 11 PTSD 1.4 1.3 0.3 0.6 0.6
## 12 Any somatoform disorder 2 1.2 2.7 1 1
## 13 Somatization disorder 0.5 0.1 1.5 0.5 0.5
## 14 Pain disorder 1.5 1.2 1.6 0.6 0.6
## 15 Eating disorders 1 0.1 0.4 0.5 0.5
## 16 Substance use disorders 12.8 7.5 8 2.4 2.4
## 17 Psychotic disorders 2.9 1.8 2.5 1 1
##################
#####Analyses#####
##################
#####################
#Any Mental Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.84 0.08 0.07
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male$Patient_ID)
Observation
## [1] 4741 100 26
round(Observation/length(KODAP_data_complete_male$Patient_ID)*100, 1)
## [1] 97.4 2.1 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 628.67, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.773893e-197
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.025387e-74
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.354386e-121
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.15347769 0.25153988 0.07236907
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 4473.3, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01682993 0.02503880
## sample estimates:
## p
## 0.02054654
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.25
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574, 2)
## [1] 0.21 0.31
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 4761.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003564934 0.007937938
## sample estimates:
## p
## 0.0053421
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.05 0.11
#####################
#Any Mood Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.89 0.06 0.05
KODAP_data_complete_male_any_mood_disorder <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete_male$ICD5_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung"),]
length(KODAP_data_complete_male_any_mood_disorder$Patient_ID)
## [1] 2984
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_any_mood_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_any_mood_disorder$Patient_ID)
Observation
## [1] 2915 58 11
round(Observation/length(KODAP_data_complete_male_any_mood_disorder$Patient_ID)*100,1)
## [1] 97.7 1.9 0.4
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 247.96, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.895501e-76
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.37731e-26
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 8.461431e-55
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.10199026 0.32591352 0.06839744
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 2754.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01491969 0.02523148
## sample estimates:
## p
## 0.019437
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.33
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.25 0.42
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 2938.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.001939974 0.006803219
## sample estimates:
## p
## 0.003686327
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.04 0.13
###########################
#Major Depressive Disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.86 0.07 0.07
KODAP_data_complete_male_MDD <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert")|
KODAP_data_complete_male$ICD5_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert"),]
length(KODAP_data_complete_male_MDD$Patient_ID)
## [1] 2669
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_MDD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_MDD$Patient_ID)
Observation
## [1] 2604 54 11
round(Observation/length(KODAP_data_complete_male_MDD$Patient_ID)*100,1)
## [1] 97.6 2.0 0.4
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 291.89, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.377908e-91
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.903859e-33
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 9.799118e-61
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.13097098 0.28045043 0.06321612
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 2455.5, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01537684 0.02651475
## sample estimates:
## p
## 0.0202323
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.28
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.21 0.37
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 2623.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.002169078 0.007604448
## sample estimates:
## p
## 0.004121394
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.06
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.12
###########################
#########Dysthymia#########
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.84 0.08 0.07
KODAP_data_complete_male_Dysthymia <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_male$ICD2_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_male$ICD3_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_male$ICD4_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete_male$ICD5_pre_clean %in% c("F34.1", "F34.10"),]
length(KODAP_data_complete_male_Dysthymia$Patient_ID)
## [1] 408
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_Dysthymia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_Dysthymia$Patient_ID)
Observation
## [1] 406 2
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_male_Dysthymia$Patient_ID)*100,1)
## [1] 99.5 0.5 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 70.932, df = 2, p-value = 3.957e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.307675e-26
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.406227e-12
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.102318e-13
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.17934055 0.05973366 0.00000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 398.06, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.000849515 0.019567205
## sample estimates:
## p
## 0.004901961
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.06
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.01 0.24
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 406, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.01162768
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.16
###########################
##Any anxiety disorder#####
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.83 0.09 0.08
KODAP_data_complete_male_any_anx_disorder <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete_male$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen"),]
length(KODAP_data_complete_male_any_anx_disorder$Patient_ID)
## [1] 1572
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_any_anx_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_any_anx_disorder$Patient_ID)
Observation
## [1] 1527 37 8
round(Observation/length(KODAP_data_complete_male_any_anx_disorder$Patient_ID)*100,1)
## [1] 97.1 2.4 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 233.65, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.158145e-73
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.536612e-27
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.213092e-46
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.17592028 0.25759384 0.06163062
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1425.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01685529 0.03263877
## sample estimates:
## p
## 0.0235369
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.18 0.36
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1538.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00236820 0.01042901
## sample estimates:
## p
## 0.005089059
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.06
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.13
#################################
##Panic Disorder/Agoraphobia#####
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.79 0.11 0.10
KODAP_data_complete_male_PanicAgora <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete_male$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung"),]
length(KODAP_data_complete_male_PanicAgora$Patient_ID)
## [1] 498
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_PanicAgora$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_PanicAgora$Patient_ID)
Observation
## [1] 476 18 4
round(Observation/length(KODAP_data_complete_male_PanicAgora$Patient_ID)*100,1)
## [1] 95.6 3.6 0.8
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 81.715, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 8.496355e-25
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.626748e-08
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.344942e-16
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.20460169 0.33317612 0.08192834
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 426.75, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02220042 0.05761352
## sample estimates:
## p
## 0.03614458
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.33
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.20 0.53
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 480.16, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.002576109 0.021886544
## sample estimates:
## p
## 0.008032129
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.08
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.22
#################################
##########Social phobia##########
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.91 0.05 0.04
KODAP_data_complete_male_socialphobia <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete_male$ICD5_pre_recode %in% c("F40.1 Soziale Phobie"),]
length(KODAP_data_complete_male_socialphobia$Patient_ID)
## [1] 743
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_socialphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_socialphobia$Patient_ID)
Observation
## [1] 734 7 2
round(Observation/length(KODAP_data_complete_male_socialphobia$Patient_ID)*100,1)
## [1] 98.8 0.9 0.3
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 57.847, df = 2, p-value = 2.746e-13
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 5.50549e-20
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.154687e-08
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 8.998588e-12
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.08906484 0.19305330 0.06103542
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 713.3, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004134465 0.020213199
## sample estimates:
## p
## 0.009421265
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.19
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.08 0.41
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 733.03, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0004663784 0.0107951039
## sample estimates:
## p
## 0.00269179
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.06
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.24
#################################
##########Specific phobia##########
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.76 0.12 0.11
KODAP_data_complete_male_specificphobia <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete_male$ICD5_pre_recode %in% c("F40.2 Spezifische Phobie"),]
length(KODAP_data_complete_male_specificphobia$Patient_ID)
## [1] 189
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_specificphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_specificphobia$Patient_ID)
Observation
## [1] 184 5
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_male_specificphobia$Patient_ID)*100,1)
## [1] 97.4 2.6 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 46.917, df = 2, p-value = 6.488e-11
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.745768e-15
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 7.830223e-06
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 6.825605e-10
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.276389 0.212262 0.000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 167.64, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00977982 0.06399206
## sample estimates:
## p
## 0.02645503
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.21
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.08 0.51
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 187.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.02482965
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.22
################################################
##########Generalized Anxiety Disorder##########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.94 0.03 0.03
KODAP_data_complete_male_GAD <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete_male$ICD5_pre_recode %in% c("F41.1 Generalisierte Angststörung"),]
length(KODAP_data_complete_male_GAD$Patient_ID)
## [1] 150
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_GAD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_GAD$Patient_ID)
Observation
## [1] 144 6
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_male_GAD$Patient_ID)*100,1)
## [1] 96 4 0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
## Warning in chisq.test(Observation, p = expected_ratios): Chi-squared
## approximation may be incorrect
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 4.8538, df = 2, p-value = 0.08831
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0.9450625
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.942317
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.0485118
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.026167 1.180960 0.000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 125.13, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01636367 0.08887123
## sample estimates:
## p
## 0.04
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 1.18
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.48 2.62
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 148.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.03112234
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 1.02
################################################
##########Obsessive compulsive disorders########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.98 0.01 0.01
KODAP_data_complete_male_OCD <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete_male$ICD5_pre_recode %in% c("F42.X Zwangsstörung"),]
length(KODAP_data_complete_male_OCD$Patient_ID)
## [1] 311
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_OCD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_OCD$Patient_ID)
Observation
## [1] 307 4
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_male_OCD$Patient_ID)*100,1)
## [1] 98.7 1.3 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
## Warning in chisq.test(Observation, p = expected_ratios): Chi-squared
## approximation may be incorrect
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 3.1764, df = 2, p-value = 0.2043
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.9608062
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.5453243
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.002337 1.614700 0.000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 293.26, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004128066 0.034853324
## sample estimates:
## p
## 0.01286174
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 1.61
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.52 4.38
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 309, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.01520958
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 2.11
################################################
##########Post traumatic stress disorder########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.84 0.08 0.08
KODAP_data_complete_male_PTSD <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete_male$ICD5_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung"),]
length(KODAP_data_complete_male_PTSD$Patient_ID)
## [1] 237
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_PTSD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_PTSD$Patient_ID)
Observation
## [1] 233 4
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_male_PTSD$Patient_ID)*100,1)
## [1] 98.3 1.7 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 36.983, df = 2, p-value = 9.315e-09
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 8.559405e-13
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 5.645795e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.417012e-08
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1724788 0.1989466 0.0000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 219.34, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005420257 0.045526571
## sample estimates:
## p
## 0.01687764
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.2
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.06 0.54
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 235, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.01988197
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.26
################################################
##########Any somatoform Disorders##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.87 0.07 0.06
KODAP_data_complete_male_Somatoform <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete_male$ICD5_pre_recode %in% c("F45.X Somatoforme Störungen"),]
length(KODAP_data_complete_male_Somatoform$Patient_ID)
## [1] 356
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_Somatoform$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_Somatoform$Patient_ID)
Observation
## [1] 340 10 6
round(Observation/length(KODAP_data_complete_male_Somatoform$Patient_ID)*100,1)
## [1] 95.5 2.8 1.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 24.399, df = 2, p-value = 5.034e-06
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.52104e-07
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.002453925
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.0001395291
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1023611 0.4001811 0.2656933
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 315.24, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01433688 0.05270533
## sample estimates:
## p
## 0.02808989
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.4
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.20 0.75
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 330.47, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.006869443 0.038159467
## sample estimates:
## p
## 0.01685393
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.27
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.11 0.60
################################################
##########Somatization disorder##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.83 0.09 0.08
KODAP_data_complete_male_Somatization <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_male$ICD2_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_male$ICD3_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_male$ICD4_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete_male$ICD5_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10"),]
length(KODAP_data_complete_male_Somatization$Patient_ID)
## [1] 72
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_Somatization$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_Somatization$Patient_ID)
Observation
## [1] 68 3 1
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_male_Somatization$Patient_ID)*100,1)
## [1] 94.4 4.2 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 9.1102, df = 2, p-value = 0.01051
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0.004472029
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.6357538
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.01198469
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.141453 0.459581 0.000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 57.69, df = 1, p-value = 3.068e-14
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01097609 0.12665763
## sample estimates:
## p
## 0.04225352
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.47
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.12 1.40
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 69.014, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.06395388
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.78
################################################
##########Pain disorder##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.89 0.06 0.05
KODAP_data_complete_male_Pain <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_male$ICD2_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_male$ICD3_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_male$ICD4_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete_male$ICD5_pre_clean %in% c("F45.4","F45.40", "F45.41"),]
length(KODAP_data_complete_male_Pain$Patient_ID)
## [1] 135
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_Pain$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_Pain$Patient_ID)
Observation
## [1] 129 2 4
round(Observation/length(KODAP_data_complete_male_Pain$Patient_ID)*100,1)
## [1] 95.6 1.5 3.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 6.8381, df = 2, p-value = 0.03274
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0.0279163
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.08032174
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.7656564
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0787432 0.2469717 0.5465752
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 125.19, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.002570188 0.057923575
## sample estimates:
## p
## 0.01481481
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.25
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.04 0.97
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 117.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.009533825 0.078775571
## sample estimates:
## p
## 0.02962963
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.55
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.18 1.45
################################################
##########Eating disorders##################
################################################
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.81 0.10 0.09
KODAP_data_complete_male_Eating <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete_male$ICD5_pre_recode %in% c("F50.X Essstörung"),]
length(KODAP_data_complete_male_Eating$Patient_ID)
## [1] 97
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_Eating$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_Eating$Patient_ID)
Observation
## [1] 95 2
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_male_Eating$Patient_ID)*100,1)
## [1] 97.9 2.1 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 17.855, df = 2, p-value = 0.0001327
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.253243e-06
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.01677083
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.0006759089
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.2045851 0.2099521 0.0000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 87.258, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003579326 0.079655349
## sample estimates:
## p
## 0.02061856
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.21
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.04 0.81
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 95.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.04747222
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.53
#########################################
##########Substance-use disorders########
#########################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.93 0.04 0.03
KODAP_data_complete_male_SubstanceUse <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete_male$ICD5_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen"),]
length(KODAP_data_complete_male_SubstanceUse$Patient_ID)
## [1] 442
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_SubstanceUse$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_SubstanceUse$Patient_ID)
Observation
## [1] 431 10 1
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_male_SubstanceUse$Patient_ID)*100,1)
## [1] 97.5 2.3 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 19.376, df = 2, p-value = 6.201e-05
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.695199e-05
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.3154647
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 9.629037e-07
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0520828 0.5887187 0.0000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 400, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01156375 0.04267376
## sample estimates:
## p
## 0.02267574
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.59
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.30 1.11
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 439, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.01076518
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.31
#########################################
##########Psychotic disorders############
#########################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "5064y"])
prevalence_1864 <- (male_amount_1834/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_1834+
(male_amount_3549/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_3549+
(male_amount_5064/sum(male_amount_1834,male_amount_3549, male_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (male_amount_1864*prevalence_1864)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (male_amount_6574*prevalence_6574)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (male_amount_75plus*prevalence_75plus)/((male_amount_1864*prevalence_1864)+(male_amount_6574*prevalence_6574)+(male_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.89 0.06 0.05
KODAP_data_complete_male_Psychotic <- KODAP_data_complete_male[KODAP_data_complete_male$ICD1_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_male$ICD2_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_male$ICD3_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_male$ICD4_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete_male$ICD5_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen"),]
length(KODAP_data_complete_male_Psychotic$Patient_ID)
## [1] 181
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_male_Psychotic$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_male_Psychotic$Patient_ID)
Observation
## [1] 176 4 1
Observation[2] <- 0
Observation[3] <- 0
round(Observation/length(KODAP_data_complete_male_Psychotic$Patient_ID)*100,1)
## [1] 97.2 0.0 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 22.578, df = 2, p-value = 1.251e-05
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.610405e-09
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.0001168851
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.0004248988
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.097117 0.000000 0.000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 174.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.02662404
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.00 0.45
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 174.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.00000000 0.02662404
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.49
Sensitivity analysis 1: Equal prevalences across age groups
#Read prevalence estimates
Prevalence_estimates <- read_excel("Prevalence_estimates.xlsx")
Prevalence_estimates$'1834y' <- 1
Prevalence_estimates$'3549y' <- 1
Prevalence_estimates$'5064y' <- 1
Prevalence_estimates$'6574y' <- 1
Prevalence_estimates$'75yplus' <- 1
Prevalence_estimates
## # A tibble: 17 × 6
## Diagnosis `1834y` `3549y` `5064y` `6574y` `75yplus`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Any mental disorder 1 1 1 1 1
## 2 Any mood disorder 1 1 1 1 1
## 3 Major Depressive Disorder 1 1 1 1 1
## 4 Dysthymia 1 1 1 1 1
## 5 Any anxiety disorder 1 1 1 1 1
## 6 Panic disorder/Agoraphobia 1 1 1 1 1
## 7 Social phobia 1 1 1 1 1
## 8 Specific phobias 1 1 1 1 1
## 9 GAD 1 1 1 1 1
## 10 OCD 1 1 1 1 1
## 11 PTSD 1 1 1 1 1
## 12 Any somatoform disorder 1 1 1 1 1
## 13 Somatization disorder 1 1 1 1 1
## 14 Pain disorder 1 1 1 1 1
## 15 Eating disorders 1 1 1 1 1
## 16 Substance use disorders 1 1 1 1 1
## 17 Psychotic disorders 1 1 1 1 1
##################
#####Analyses#####
##################
#####################
#Any Mental Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete$Patient_ID)
Observation
## [1] 13218 324 93
round(Observation/length(KODAP_data_complete$Patient_ID)*100, 1)
## [1] 96.9 2.4 0.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 3832.9, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.482197e-323
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.482197e-323
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.482197e-323
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.31665260 0.18427180 0.05060858
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 12368, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02130213 0.02649473
## sample estimates:
## p
## 0.02376238
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.18
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574, 2)
## [1] 0.17 0.21
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 13264, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005538338 0.008388176
## sample estimates:
## p
## 0.006820682
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.04 0.06
#####################
#Any Mood Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_any_mood_disorder <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung"),]
length(KODAP_data_complete_any_mood_disorder$Patient_ID)
## [1] 8244
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_mood_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_mood_disorder$Patient_ID)
Observation
## [1] 8027 179 38
round(Observation/length(KODAP_data_complete_any_mood_disorder$Patient_ID)*100,1)
## [1] 97.4 2.2 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 2402.7, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.482197e-323
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.179034e-269
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.482197e-323
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.32243969 0.16837750 0.03420125
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 7541.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01872596 0.02515365
## sample estimates:
## p
## 0.02171276
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.17
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.15 0.20
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 8090.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003309074 0.006390114
## sample estimates:
## p
## 0.004609413
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.03
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.02 0.05
###########################
#Major Depressive Disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_MDD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD2_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD3_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD4_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert")|
KODAP_data_complete$ICD5_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert"),]
length(KODAP_data_complete_MDD$Patient_ID)
## [1] 7460
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_MDD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_MDD$Patient_ID)
Observation
## [1] 7261 163 36
round(Observation/length(KODAP_data_complete_MDD$Patient_ID)*100,1)
## [1] 97.3 2.2 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 2167.7, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.482197e-323
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.563341e-243
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.482197e-323
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.32195967 0.16944072 0.03580635
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 6820.3, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01870821 0.02549363
## sample estimates:
## p
## 0.02184987
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.17
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.15 0.20
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 7314.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003431670 0.006750952
## sample estimates:
## p
## 0.004825737
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.04
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.05
###########################
#########Dysthymia#########
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_Dysthymia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD2_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD3_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD4_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD5_pre_clean %in% c("F34.1", "F34.10"),]
length(KODAP_data_complete_Dysthymia$Patient_ID)
## [1] 958
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Dysthymia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Dysthymia$Patient_ID)
Observation
## [1] 935 22 1
round(Observation/length(KODAP_data_complete_Dysthymia$Patient_ID)*100,1)
## [1] 97.6 2.3 0.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 285.35, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.129894e-91
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.795348e-31
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 4.999601e-58
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.325582304 0.178084528 0.007745168
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 870.11, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01479694 0.03514765
## sample estimates:
## p
## 0.02296451
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.18
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.11 0.27
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 952.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 5.449108e-05 6.751188e-03
## sample estimates:
## p
## 0.001043841
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.01
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.05
###########################
##Any anxiety disorder#####
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_any_anx_disorder <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen"),]
length(KODAP_data_complete_any_anx_disorder$Patient_ID)
## [1] 4453
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_anx_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_anx_disorder$Patient_ID)
Observation
## [1] 4318 106 29
round(Observation/length(KODAP_data_complete_any_anx_disorder$Patient_ID)*100,1)
## [1] 97.0 2.4 0.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 1254.8, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.074186e-138
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.350017e-228
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.31701445 0.18459596 0.04832164
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 4037.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01961854 0.02883120
## sample estimates:
## p
## 0.02380418
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.18
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.15 0.22
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 4335.8, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004446095 0.009469305
## sample estimates:
## p
## 0.006512464
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.07
#################################
##Panic Disorder/Agoraphobia#####
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_PanicAgora <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung"),]
length(KODAP_data_complete_PanicAgora$Patient_ID)
## [1] 1456
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PanicAgora$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PanicAgora$Patient_ID)
Observation
## [1] 1400 47 9
round(Observation/length(KODAP_data_complete_PanicAgora$Patient_ID)*100,1)
## [1] 96.2 3.2 0.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 384.51, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.325822e-116
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.524164e-37
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 8.424431e-76
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.30595213 0.25032574 0.04586458
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1272.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02406506 0.04304906
## sample estimates:
## p
## 0.03228022
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.25
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.19 0.33
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1418.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003019616 0.012152642
## sample estimates:
## p
## 0.006181319
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.02 0.09
#################################
##########Social phobia##########
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_socialphobia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.1 Soziale Phobie"),]
length(KODAP_data_complete_socialphobia$Patient_ID)
## [1] 1850
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_socialphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_socialphobia$Patient_ID)
Observation
## [1] 1830 16 4
round(Observation/length(KODAP_data_complete_socialphobia$Patient_ID)*100,1)
## [1] 98.9 0.9 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 609.76, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 5.845015e-208
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.092294e-85
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 6.289734e-108
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.34350707 0.06706830 0.01604296
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1784.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005124665 0.014335622
## sample estimates:
## p
## 0.008648649
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.04 0.11
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1832, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0006928545 0.0059315037
## sample estimates:
## p
## 0.002162162
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.02
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.04
#################################
##########Specific phobia##########
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_specificphobia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.2 Spezifische Phobie"),]
length(KODAP_data_complete_specificphobia$Patient_ID)
## [1] 703
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_specificphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_specificphobia$Patient_ID)
Observation
## [1] 678 22 3
round(Observation/length(KODAP_data_complete_specificphobia$Patient_ID)*100,1)
## [1] 96.4 3.1 0.4
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 190.54, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 8.387325e-59
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 7.026761e-19
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 9.582599e-39
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.30989042 0.24268133 0.03166374
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 615.88, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02018695 0.04777189
## sample estimates:
## p
## 0.03129445
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.24
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.16 0.37
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 689.07, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.001102765 0.013513634
## sample estimates:
## p
## 0.004267425
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.03
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.10
################################################
##########Generalized Anxiety Disorder##########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_GAD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F41.1 Generalisierte Angststörung"),]
length(KODAP_data_complete_GAD$Patient_ID)
## [1] 552
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_GAD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_GAD$Patient_ID)
Observation
## [1] 526 20 6
round(Observation/length(KODAP_data_complete_GAD$Patient_ID)*100,1)
## [1] 95.3 3.6 1.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 134.86, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.643319e-40
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.419061e-13
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.69178e-26
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.29421748 0.28096999 0.08065077
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 473.05, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02285853 0.05637906
## sample estimates:
## p
## 0.03623188
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.28
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.18 0.44
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 526.31, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004426108 0.024731112
## sample estimates:
## p
## 0.01086957
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.08
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.18
################################################
##########Obsessive compulsive disorders########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_OCD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F42.X Zwangsstörung"),]
length(KODAP_data_complete_OCD$Patient_ID)
## [1] 791
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_OCD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_OCD$Patient_ID)
Observation
## [1] 778 11 2
round(Observation/length(KODAP_data_complete_OCD$Patient_ID)*100,1)
## [1] 98.4 1.4 0.3
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 249.53, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.157589e-83
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.687856e-32
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 7.111026e-46
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.33586850 0.10784133 0.01876073
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 745.67, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.007329893 0.025530476
## sample estimates:
## p
## 0.01390645
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.11
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.06 0.20
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 781.03, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0004380695 0.0101435327
## sample estimates:
## p
## 0.002528445
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.02
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.08
################################################
##########Post traumatic stress disorder########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_PTSD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung"),]
length(KODAP_data_complete_PTSD$Patient_ID)
## [1] 1067
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PTSD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PTSD$Patient_ID)
Observation
## [1] 1052 13 2
round(Observation/length(KODAP_data_complete_PTSD$Patient_ID)*100,1)
## [1] 98.6 1.2 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 342.99, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.380815e-115
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.537755e-45
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 6.614146e-63
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.33909663 0.09448175 0.01390791
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1013.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.006788272 0.021319397
## sample estimates:
## p
## 0.01218369
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.09
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.05 0.17
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1057, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0003247314 0.0075301326
## sample estimates:
## p
## 0.001874414
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.01
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.06
################################################
##########Any somatoform Disorders##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_Somatoform <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F45.X Somatoforme Störungen"),]
length(KODAP_data_complete_Somatoform$Patient_ID)
## [1] 1074
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Somatoform$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Somatoform$Patient_ID)
Observation
## [1] 1009 48 17
round(Observation/length(KODAP_data_complete_Somatoform$Patient_ID)*100,1)
## [1] 93.9 4.5 1.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 232.11, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.559916e-66
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.846748e-20
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.480989e-44
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.2759906 0.3465820 0.1174467
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 888.76, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03347037 0.05928157
## sample estimates:
## p
## 0.04469274
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.35
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.26 0.46
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1005.1, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.009547387 0.025770512
## sample estimates:
## p
## 0.01582868
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.12
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.07 0.19
################################################
##########Somatization disorder##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_Somatization <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD2_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD3_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD4_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD5_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10"),]
length(KODAP_data_complete_Somatization$Patient_ID)
## [1] 211
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Somatization$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Somatization$Patient_ID)
Observation
## [1] 203 7 1
round(Observation/length(KODAP_data_complete_Somatization$Patient_ID)*100,1)
## [1] 96.2 3.3 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 56.095, df = 2, p-value = 6.593e-13
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.132822e-17
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 8.006803e-06
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.235903e-11
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.30669485 0.25726731 0.03516526
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 182.07, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01461394 0.06996360
## sample estimates:
## p
## 0.03317536
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.11 0.54
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 205.04, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0002474437 0.0302007408
## sample estimates:
## p
## 0.004739336
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.04
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.22
################################################
##########Pain disorder##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_Pain <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD2_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD3_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD4_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD5_pre_clean %in% c("F45.4","F45.40", "F45.41"),]
length(KODAP_data_complete_Pain$Patient_ID)
## [1] 508
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Pain$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Pain$Patient_ID)
Observation
## [1] 465 30 13
round(Observation/length(KODAP_data_complete_Pain$Patient_ID)*100,1)
## [1] 91.5 5.9 2.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 86.307, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 7.568767e-24
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.174023e-06
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.261151e-17
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.2432253 0.4579590 0.1898786
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 393.32, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.04085658 0.08418493
## sample estimates:
## p
## 0.05905512
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.46
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.32 0.65
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 455.44, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01428679 0.04450754
## sample estimates:
## p
## 0.02559055
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.19
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.11 0.33
################################################
##########Eating disorders##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_Eating <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F50.X Essstörung"),]
length(KODAP_data_complete_Eating$Patient_ID)
## [1] 857
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Eating$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Eating$Patient_ID)
Observation
## [1] 849 8
Observation[3] <- 0
Observation
## [1] 849 8 0
round(Observation/length(KODAP_data_complete_Eating$Patient_ID)*100,1)
## [1] 99.1 0.9 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 285.92, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 9.019125e-99
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.615027e-39
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 7.956119e-54
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.34551166 0.07238993 0.00000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 823.34, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004346906 0.019076925
## sample estimates:
## p
## 0.009334889
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.03 0.15
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 855, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.000000000 0.005563187
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.04
#########################################
##########Substance-use disorders########
#########################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_SubstanceUse <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen"),]
length(KODAP_data_complete_SubstanceUse$Patient_ID)
## [1] 764
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_SubstanceUse$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_SubstanceUse$Patient_ID)
Observation
## [1] 748 15 1
round(Observation/length(KODAP_data_complete_SubstanceUse$Patient_ID)*100,1)
## [1] 97.9 2.0 0.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 232.94, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 6.715239e-76
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 5.148797e-27
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.919025e-46
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.329746437 0.152253372 0.009711872
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 703.26, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01143871 0.03294463
## sample estimates:
## p
## 0.01963351
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.15
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.09 0.26
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 758.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 6.832858e-05 8.456433e-03
## sample estimates:
## p
## 0.001308901
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.01
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.06
#########################################
##########Psychotic disorders############
#########################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.74 0.13 0.13
KODAP_data_complete_Psychotic <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen"),]
length(KODAP_data_complete_Psychotic$Patient_ID)
## [1] 336
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Psychotic$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Psychotic$Patient_ID)
Observation
## [1] 331 4 1
round(Observation/length(KODAP_data_complete_Psychotic$Patient_ID)*100,1)
## [1] 98.5 1.2 0.3
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 107.26, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.100542e-36
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 9.229047e-15
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.52678e-19
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.33797905 0.09231871 0.02208295
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 318.24, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003820372 0.032295397
## sample estimates:
## p
## 0.01190476
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.09
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.03 0.25
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 330.03, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0001553772 0.0190996535
## sample estimates:
## p
## 0.00297619
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.02
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.14
Sensitivity analysis 2: Lower prevalences in old-old compared to
young-old adults
#Read prevalence estimates
Prevalence_estimates <- read_excel("Prevalence_estimates.xlsx")
Prevalence_estimates_v2 <- Prevalence_estimates
Prevalence_estimates_v2$'75yplus' <- 0.5*Prevalence_estimates_v2$'75yplus'
Prevalence_estimates_v2
## # A tibble: 17 × 6
## Diagnosis `1834y` `3549y` `5064y` `6574y` `75yplus`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Any mental disorder 35.8 28 26.4 19.6 9.8
## 2 Any mood disorder 15.1 10.3 7 5.9 2.95
## 3 Major Depressive Disorder 10 7.2 5.2 4.4 2.2
## 4 Dysthymia 2.1 1.7 1.3 1.6 0.8
## 5 Any anxiety disorder 18.1 16.2 15.3 11.1 5.55
## 6 Panic disorder/Agoraphobia 4.2 4.1 4.1 3.5 1.75
## 7 Social phobia 4.6 3.1 2.2 0.7 0.35
## 8 Specific phobias 12.3 9.5 10.9 8.4 4.2
## 9 GAD 3.3 2 2.3 1.3 0.65
## 10 OCD 7.2 3.6 2.2 1.1 0.55
## 11 PTSD 3.7 2.5 1 1.8 0.9
## 12 Any somatoform disorder 4.2 3.8 3.6 2.1 1.05
## 13 Somatization disorder 0.9 0.6 0.9 0.8 0.4
## 14 Pain disorder 4 3.8 3 1.6 0.8
## 15 Eating disorders 2.3 0.5 0.7 0.4 0.2
## 16 Substance use disorders 8.4 5.9 5.5 2.5 1.25
## 17 Psychotic disorders 4.2 2.2 2.5 1.3 0.65
##################
#####Analyses#####
##################
#####################
#Any Mental Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any mental disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any mental disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any mental disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any mental disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any mental disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.85 0.10 0.05
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete$Patient_ID)
Observation
## [1] 13218 324 93
round(Observation/length(KODAP_data_complete$Patient_ID)*100, 1)
## [1] 96.9 2.4 0.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 1506.9, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.482197e-323
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.806245e-257
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.404068e-187
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1386400 0.2434408 0.1337176
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 12368, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02130213 0.02649473
## sample estimates:
## p
## 0.02376238
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.24
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574, 2)
## [1] 0.22 0.27
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 13264, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005538338 0.008388176
## sample estimates:
## p
## 0.006820682
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.13
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.11 0.16
#####################
#Any Mood Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any mood disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any mood disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any mood disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any mood disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any mood disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.87 0.08 0.04
KODAP_data_complete_any_mood_disorder <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung"),]
length(KODAP_data_complete_any_mood_disorder$Patient_ID)
## [1] 8244
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_mood_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_mood_disorder$Patient_ID)
Observation
## [1] 8027 179 38
round(Observation/length(KODAP_data_complete_any_mood_disorder$Patient_ID)*100,1)
## [1] 97.4 2.2 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 777.85, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 9.008437e-240
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.726796e-128
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.391126e-108
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1177238 0.2565222 0.1042108
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 7541.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01872596 0.02515365
## sample estimates:
## p
## 0.02171276
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.22 0.30
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 8090.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003309074 0.006390114
## sample estimates:
## p
## 0.004609413
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.1
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.07 0.14
###########################
#Major Depressive Disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Major Depressive Disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Major Depressive Disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Major Depressive Disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Major Depressive Disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Major Depressive Disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.86 0.09 0.05
KODAP_data_complete_MDD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD2_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD3_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD4_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert")|
KODAP_data_complete$ICD5_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert"),]
length(KODAP_data_complete_MDD$Patient_ID)
## [1] 7460
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_MDD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_MDD$Patient_ID)
Observation
## [1] 7261 163 36
round(Observation/length(KODAP_data_complete_MDD$Patient_ID)*100,1)
## [1] 97.3 2.2 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 775.99, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.352649e-240
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.493828e-130
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.27984e-105
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1283336 0.2421618 0.1023476
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 6820.3, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01870821 0.02549363
## sample estimates:
## p
## 0.02184987
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.24
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.21 0.28
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 7314.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003431670 0.006750952
## sample estimates:
## p
## 0.004825737
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.1
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.07 0.14
###########################
#########Dysthymia#########
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Dysthymia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Dysthymia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Dysthymia", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Dysthymia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Dysthymia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.80 0.13 0.07
KODAP_data_complete_Dysthymia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD2_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD3_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD4_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD5_pre_clean %in% c("F34.1", "F34.10"),]
length(KODAP_data_complete_Dysthymia$Patient_ID)
## [1] 958
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Dysthymia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Dysthymia$Patient_ID)
Observation
## [1] 935 22 1
round(Observation/length(KODAP_data_complete_Dysthymia$Patient_ID)*100,1)
## [1] 97.6 2.3 0.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 189.92, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 9.767317e-62
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.068134e-32
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.857502e-28
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.22364321 0.17276174 0.01502734
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 870.11, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01479694 0.03514765
## sample estimates:
## p
## 0.02296451
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.17
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.11 0.26
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 952.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 5.449108e-05 6.751188e-03
## sample estimates:
## p
## 0.001043841
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.02
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.0 0.1
###########################
##Any anxiety disorder#####
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any anxiety disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any anxiety disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any anxiety disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any anxiety disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any anxiety disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.85 0.10 0.05
KODAP_data_complete_any_anx_disorder <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen"),]
length(KODAP_data_complete_any_anx_disorder$Patient_ID)
## [1] 4453
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_anx_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_anx_disorder$Patient_ID)
Observation
## [1] 4318 106 29
round(Observation/length(KODAP_data_complete_any_anx_disorder$Patient_ID)*100,1)
## [1] 97.0 2.4 0.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 514.84, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.160606e-158
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.341044e-88
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.479462e-65
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1438131 0.2380740 0.1246411
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 4037.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01961854 0.02883120
## sample estimates:
## p
## 0.02380418
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.24
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.20 0.29
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 4335.8, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004446095 0.009469305
## sample estimates:
## p
## 0.006512464
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.12
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.09 0.18
#################################
##Panic Disorder/Agoraphobia#####
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Panic disorder/Agoraphobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Panic disorder/Agoraphobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Panic disorder/Agoraphobia", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Panic disorder/Agoraphobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Panic disorder/Agoraphobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.82 0.12 0.06
KODAP_data_complete_PanicAgora <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung"),]
length(KODAP_data_complete_PanicAgora$Patient_ID)
## [1] 1456
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PanicAgora$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PanicAgora$Patient_ID)
Observation
## [1] 1400 47 9
round(Observation/length(KODAP_data_complete_PanicAgora$Patient_ID)*100,1)
## [1] 96.2 3.2 0.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 207.6, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 5.549702e-63
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 5.581766e-33
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 8.70023e-29
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1787030 0.2667648 0.0977531
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1272.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02406506 0.04304906
## sample estimates:
## p
## 0.03228022
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.27
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.20 0.36
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1418.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003019616 0.012152642
## sample estimates:
## p
## 0.006181319
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.1
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.05 0.19
#################################
##########Social phobia##########
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Social phobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Social phobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Social phobia", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Social phobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Social phobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.95 0.04 0.02
KODAP_data_complete_socialphobia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.1 Soziale Phobie"),]
length(KODAP_data_complete_socialphobia$Patient_ID)
## [1] 1850
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_socialphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_socialphobia$Patient_ID)
Observation
## [1] 1830 16 4
round(Observation/length(KODAP_data_complete_socialphobia$Patient_ID)*100,1)
## [1] 98.9 0.9 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 68.426, df = 2, p-value = 1.385e-15
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.597859e-22
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 5.007926e-13
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 4.090319e-10
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0459446 0.2426759 0.1160978
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1784.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005124665 0.014335622
## sample estimates:
## p
## 0.008648649
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.24
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.14 0.40
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1832, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0006928545 0.0059315037
## sample estimates:
## p
## 0.002162162
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.12
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.04 0.32
#################################
##########Specific phobia##########
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Specific phobias", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Specific phobias", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Specific phobias", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Specific phobias", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Specific phobias", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.83 0.11 0.06
KODAP_data_complete_specificphobia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.2 Spezifische Phobie"),]
length(KODAP_data_complete_specificphobia$Patient_ID)
## [1] 703
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_specificphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_specificphobia$Patient_ID)
Observation
## [1] 678 22 3
round(Observation/length(KODAP_data_complete_specificphobia$Patient_ID)*100,1)
## [1] 96.4 3.1 0.4
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 91.277, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.456607e-28
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.164906e-14
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 4.063969e-14
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.16208570 0.28015003 0.07310491
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 615.88, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02018695 0.04777189
## sample estimates:
## p
## 0.03129445
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.28
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.18 0.43
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 689.07, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.001102765 0.013513634
## sample estimates:
## p
## 0.004267425
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.02 0.23
################################################
##########Generalized Anxiety Disorder##########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "GAD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "GAD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "GAD", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "GAD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "GAD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.88 0.08 0.04
KODAP_data_complete_GAD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F41.1 Generalisierte Angststörung"),]
length(KODAP_data_complete_GAD$Patient_ID)
## [1] 552
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_GAD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_GAD$Patient_ID)
Observation
## [1] 526 20 6
round(Observation/length(KODAP_data_complete_GAD$Patient_ID)*100,1)
## [1] 95.3 3.6 1.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 28.541, df = 2, p-value = 6.345e-07
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.779346e-08
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.0001577275
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.0001774772
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0832576 0.4584141 0.2631701
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 473.05, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02285853 0.05637906
## sample estimates:
## p
## 0.03623188
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.46
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.29 0.71
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 526.31, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004426108 0.024731112
## sample estimates:
## p
## 0.01086957
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.11 0.60
################################################
##########Obsessive compulsive disorders########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "OCD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "OCD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "OCD", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "OCD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "OCD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.94 0.04 0.02
KODAP_data_complete_OCD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F42.X Zwangsstörung"),]
length(KODAP_data_complete_OCD$Patient_ID)
## [1] 791
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_OCD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_OCD$Patient_ID)
Observation
## [1] 778 11 2
round(Observation/length(KODAP_data_complete_OCD$Patient_ID)*100,1)
## [1] 98.4 1.4 0.3
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 30.859, df = 2, p-value = 1.991e-07
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 5.083752e-10
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.499091e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.579006e-05
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0514433 0.3279810 0.1141151
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 745.67, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.007329893 0.025530476
## sample estimates:
## p
## 0.01390645
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.33
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.17 0.60
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 781.03, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0004380695 0.0101435327
## sample estimates:
## p
## 0.002528445
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.11
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.02 0.46
################################################
##########Post traumatic stress disorder########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "PTSD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "PTSD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "PTSD", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "PTSD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "PTSD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.83 0.11 0.06
KODAP_data_complete_PTSD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung"),]
length(KODAP_data_complete_PTSD$Patient_ID)
## [1] 1067
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PTSD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PTSD$Patient_ID)
Observation
## [1] 1052 13 2
round(Observation/length(KODAP_data_complete_PTSD$Patient_ID)*100,1)
## [1] 98.6 1.2 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 185.08, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 9.512809e-64
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.061882e-37
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.505605e-24
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.18878952 0.10871529 0.03200623
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1013.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.006788272 0.021319397
## sample estimates:
## p
## 0.01218369
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.11
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.06 0.19
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1057, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0003247314 0.0075301326
## sample estimates:
## p
## 0.001874414
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.03
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.13
################################################
##########Any somatoform Disorders##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any somatoform disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any somatoform disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any somatoform disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any somatoform disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Any somatoform disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.87 0.08 0.04
KODAP_data_complete_Somatoform <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F45.X Somatoforme Störungen"),]
length(KODAP_data_complete_Somatoform$Patient_ID)
## [1] 1074
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Somatoform$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Somatoform$Patient_ID)
Observation
## [1] 1009 48 17
round(Observation/length(KODAP_data_complete_Somatoform$Patient_ID)*100,1)
## [1] 93.9 4.5 1.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 43.547, df = 2, p-value = 3.499e-10
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.411975e-12
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 3.105672e-06
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.928161e-06
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0759256 0.5365769 0.3636612
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 888.76, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03347037 0.05928157
## sample estimates:
## p
## 0.04469274
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.54
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.40 0.71
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1005.1, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.009547387 0.025770512
## sample estimates:
## p
## 0.01582868
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.36
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.22 0.59
################################################
##########Somatization disorder##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Somatization disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Somatization disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Somatization disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Somatization disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Somatization disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.79 0.14 0.07
KODAP_data_complete_Somatization <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD2_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD3_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD4_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD5_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10"),]
length(KODAP_data_complete_Somatization$Patient_ID)
## [1] 211
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Somatization$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Somatization$Patient_ID)
Observation
## [1] 203 7 1
round(Observation/length(KODAP_data_complete_Somatization$Patient_ID)*100,1)
## [1] 96.2 3.3 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 37.568, df = 2, p-value = 6.952e-09
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 4.922326e-12
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.806064e-06
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.719855e-05
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.21580233 0.24205029 0.06617057
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 182.07, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01461394 0.06996360
## sample estimates:
## p
## 0.03317536
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.24
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.11 0.51
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 205.04, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0002474437 0.0302007408
## sample estimates:
## p
## 0.004739336
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.42
################################################
##########Pain disorder##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Pain disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Pain disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Pain disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Pain disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Pain disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.89 0.07 0.04
KODAP_data_complete_Pain <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD2_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD3_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD4_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD5_pre_clean %in% c("F45.4","F45.40", "F45.41"),]
length(KODAP_data_complete_Pain$Patient_ID)
## [1] 508
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Pain$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Pain$Patient_ID)
Observation
## [1] 465 30 13
round(Observation/length(KODAP_data_complete_Pain$Patient_ID)*100,1)
## [1] 91.5 5.9 2.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 2.8689, df = 2, p-value = 0.2382
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0.3414028
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.153037
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.7069781
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0248165 0.8418143 0.6980647
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 393.32, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.04085658 0.08418493
## sample estimates:
## p
## 0.05905512
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.84
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.58 1.20
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 455.44, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01428679 0.04450754
## sample estimates:
## p
## 0.02559055
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.7
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.39 1.21
################################################
##########Eating disorders##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Eating disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Eating disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Eating disorders", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Eating disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Eating disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.92 0.06 0.03
KODAP_data_complete_Eating <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F50.X Essstörung"),]
length(KODAP_data_complete_Eating$Patient_ID)
## [1] 857
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Eating$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Eating$Patient_ID)
Observation
## [1] 849 8
Observation[3] <- 0
Observation
## [1] 849 8 0
round(Observation/length(KODAP_data_complete_Eating$Patient_ID)*100,1)
## [1] 99.1 0.9 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 62.799, df = 2, p-value = 2.308e-14
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.8057e-22
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.234246e-12
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 7.938637e-11
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0818019 0.1687097 0.0000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 823.34, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004346906 0.019076925
## sample estimates:
## p
## 0.009334889
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.17
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.08 0.34
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 855, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.000000000 0.005563187
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.19
#########################################
##########Substance-use disorders########
#########################################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Substance use disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Substance use disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Substance use disorders", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Substance use disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Substance use disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.91 0.06 0.03
KODAP_data_complete_SubstanceUse <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen"),]
length(KODAP_data_complete_SubstanceUse$Patient_ID)
## [1] 764
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_SubstanceUse$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_SubstanceUse$Patient_ID)
Observation
## [1] 748 15 1
round(Observation/length(KODAP_data_complete_SubstanceUse$Patient_ID)*100,1)
## [1] 97.9 2.0 0.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 47.616, df = 2, p-value = 4.573e-11
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 5.153667e-15
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 2.423304e-07
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.750416e-09
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0784913 0.3242332 0.0413641
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 703.26, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01143871 0.03294463
## sample estimates:
## p
## 0.01963351
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.32
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.19 0.54
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 758.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 6.832858e-05 8.456433e-03
## sample estimates:
## p
## 0.001308901
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.04
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.27
#########################################
##########Psychotic disorders############
#########################################
prevalence_1834 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Psychotic disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Psychotic disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Psychotic disorders", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Psychotic disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates_v2[Prevalence_estimates_v2$Diagnosis == "Psychotic disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864*prevalence_1864)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574*prevalence_6574)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus*prevalence_75plus)/((census_amount_1864*prevalence_1864)+(census_amount_6574*prevalence_6574)+(census_amount_75plus*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.90 0.07 0.04
KODAP_data_complete_Psychotic <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen"),]
length(KODAP_data_complete_Psychotic$Patient_ID)
## [1] 336
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Psychotic$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Psychotic$Patient_ID)
Observation
## [1] 331 4 1
round(Observation/length(KODAP_data_complete_Psychotic$Patient_ID)*100,1)
## [1] 98.5 1.2 0.3
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 29.017, df = 2, p-value = 5.001e-07
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.983926e-10
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.083205e-06
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.000311267
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.10042947 0.17297806 0.08275387
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 318.24, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003820372 0.032295397
## sample estimates:
## p
## 0.01190476
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.17
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.06 0.47
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 330.03, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0001553772 0.0190996535
## sample estimates:
## p
## 0.00297619
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.08
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.53
Sensitivity analysis 3: Influence of long-term care needs
#Read prevalence estimates
Prevalence_estimates <- read_excel("Prevalence_estimates.xlsx")
Prevalence_estimates
## # A tibble: 17 × 6
## Diagnosis `1834y` `3549y` `5064y` `6574y` `75yplus`
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Any mental disorder 35.8 28 26.4 19.6 19.6
## 2 Any mood disorder 15.1 10.3 7 5.9 5.9
## 3 Major Depressive Disorder 10 7.2 5.2 4.4 4.4
## 4 Dysthymia 2.1 1.7 1.3 1.6 1.6
## 5 Any anxiety disorder 18.1 16.2 15.3 11.1 11.1
## 6 Panic disorder/Agoraphobia 4.2 4.1 4.1 3.5 3.5
## 7 Social phobia 4.6 3.1 2.2 0.7 0.7
## 8 Specific phobias 12.3 9.5 10.9 8.4 8.4
## 9 GAD 3.3 2 2.3 1.3 1.3
## 10 OCD 7.2 3.6 2.2 1.1 1.1
## 11 PTSD 3.7 2.5 1 1.8 1.8
## 12 Any somatoform disorder 4.2 3.8 3.6 2.1 2.1
## 13 Somatization disorder 0.9 0.6 0.9 0.8 0.8
## 14 Pain disorder 4 3.8 3 1.6 1.6
## 15 Eating disorders 2.3 0.5 0.7 0.4 0.4
## 16 Substance use disorders 8.4 5.9 5.5 2.5 2.5
## 17 Psychotic disorders 4.2 2.2 2.5 1.3 1.3
##################
#####Analyses#####
##################
#####################
#Any Mental Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mental disorder", "75yplus"])
census_amount_1864_LTC <- census_amount_1864*(1-Long_term_care_rate_1864_average)
census_amount_6574_LTC <- census_amount_6574*(1-Long_term_care_rate_6574_average)
census_amount_75plus_LTC <- census_amount_75plus*(1-Long_term_care_rate_75plus_average)
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.84 0.09 0.07
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete$Patient_ID)
Observation
## [1] 13218 324 93
round(Observation/length(KODAP_data_complete$Patient_ID)*100, 1)
## [1] 96.9 2.4 0.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 1725, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.482197e-323
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.395244e-225
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.324963e-291
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.15497259 0.26077571 0.09808828
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 12368, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02130213 0.02649473
## sample estimates:
## p
## 0.02376238
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574, 2)
## [1] 0.23 0.29
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 13264, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005538338 0.008388176
## sample estimates:
## p
## 0.006820682
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.1
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.08 0.12
#####################
#Any Mood Disorder#
#####################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any mood disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.86 0.08 0.06
KODAP_data_complete_any_mood_disorder <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F30.X F31.X Manische Episode oder Bipolare Störungen",
"F31.7 Bipolare affktive Störung, gegenwärtig remittiert",
"F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert",
"F34 Anhaltende affektive Störungen",
"F38.X Andere affektive Störung"),]
length(KODAP_data_complete_any_mood_disorder$Patient_ID)
## [1] 8244
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_mood_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_mood_disorder$Patient_ID)
Observation
## [1] 8027 179 38
round(Observation/length(KODAP_data_complete_any_mood_disorder$Patient_ID)*100,1)
## [1] 97.4 2.2 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 891.56, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.309088e-275
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 8.323006e-113
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.856054e-164
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.13162641 0.27427242 0.07630004
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 7541.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01872596 0.02515365
## sample estimates:
## p
## 0.02171276
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.27
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.24 0.32
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 8090.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003309074 0.006390114
## sample estimates:
## p
## 0.004609413
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.08
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.05 0.11
###########################
#Major Depressive Disorder#
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Major Depressive Disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.85 0.08 0.06
KODAP_data_complete_MDD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD2_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD3_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert") |
KODAP_data_complete$ICD4_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert")|
KODAP_data_complete$ICD5_pre_recode %in% c("F32 Depressive Episode",
"F33 Rezidivierende depressive Störung",
"F33.4 Rezidivierende depressive Störung, gegenwärtig remittiert"),]
length(KODAP_data_complete_MDD$Patient_ID)
## [1] 7460
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_MDD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_MDD$Patient_ID)
Observation
## [1] 7261 163 36
round(Observation/length(KODAP_data_complete_MDD$Patient_ID)*100,1)
## [1] 97.3 2.2 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 886.4, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.229158e-275
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 6.302609e-115
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.181828e-159
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.1432943 0.2591282 0.0749966
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 6820.3, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01870821 0.02549363
## sample estimates:
## p
## 0.02184987
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.22 0.30
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 7314.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003431670 0.006750952
## sample estimates:
## p
## 0.004825737
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.05 0.10
###########################
#########Dysthymia#########
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Dysthymia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.78 0.12 0.09
KODAP_data_complete_Dysthymia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD2_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD3_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD4_pre_clean %in% c("F34.1", "F34.10") |
KODAP_data_complete$ICD5_pre_clean %in% c("F34.1", "F34.10"),]
length(KODAP_data_complete_Dysthymia$Patient_ID)
## [1] 958
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Dysthymia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Dysthymia$Patient_ID)
Observation
## [1] 935 22 1
round(Observation/length(KODAP_data_complete_Dysthymia$Patient_ID)*100,1)
## [1] 97.6 2.3 0.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 212.56, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 7.423182e-69
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 6.365835e-29
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.660416e-39
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.24754529 0.18601057 0.01107967
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 870.11, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01479694 0.03514765
## sample estimates:
## p
## 0.02296451
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.19
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.12 0.28
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 952.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 5.449108e-05 6.751188e-03
## sample estimates:
## p
## 0.001043841
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.01
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.07
###########################
##Any anxiety disorder#####
###########################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any anxiety disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.84 0.09 0.07
KODAP_data_complete_any_anx_disorder <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung",
"F40.1 Soziale Phobie",
"F40.2 Spezifische Phobie",
"F41.1 Generalisierte Angststörung",
"F41.X F40.9 Andere phobische oder Angststörungen"),]
length(KODAP_data_complete_any_anx_disorder$Patient_ID)
## [1] 4453
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_any_anx_disorder$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_any_anx_disorder$Patient_ID)
Observation
## [1] 4318 106 29
round(Observation/length(KODAP_data_complete_any_anx_disorder$Patient_ID)*100,1)
## [1] 97.0 2.4 0.7
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 588.25, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.925044e-181
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 9.40372e-78
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.508303e-100
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.16061923 0.25511451 0.09146172
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 4037.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01961854 0.02883120
## sample estimates:
## p
## 0.02380418
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.21 0.31
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 4335.8, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004446095 0.009469305
## sample estimates:
## p
## 0.006512464
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.09
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.06 0.13
#################################
##Panic Disorder/Agoraphobia#####
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Panic disorder/Agoraphobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.80 0.11 0.09
KODAP_data_complete_PanicAgora <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.0X F41.0 Agoraphobie/Panikstörung"),]
length(KODAP_data_complete_PanicAgora$Patient_ID)
## [1] 1456
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PanicAgora$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PanicAgora$Patient_ID)
Observation
## [1] 1400 47 9
round(Observation/length(KODAP_data_complete_PanicAgora$Patient_ID)*100,1)
## [1] 96.2 3.2 0.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 237.65, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 5.397963e-72
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.296736e-28
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.769212e-43
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.19966264 0.28672917 0.07194963
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1272.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02406506 0.04304906
## sample estimates:
## p
## 0.03228022
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.29
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.21 0.38
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1418.2, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003019616 0.012152642
## sample estimates:
## p
## 0.006181319
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.07
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.04 0.14
#################################
##########Social phobia##########
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Social phobia", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.94 0.03 0.03
KODAP_data_complete_socialphobia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.1 Soziale Phobie") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.1 Soziale Phobie"),]
length(KODAP_data_complete_socialphobia$Patient_ID)
## [1] 1850
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_socialphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_socialphobia$Patient_ID)
Observation
## [1] 1830 16 4
round(Observation/length(KODAP_data_complete_socialphobia$Patient_ID)*100,1)
## [1] 98.9 0.9 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 78.562, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 5.45309e-26
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.212814e-11
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 2.086187e-15
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.05142230 0.25762242 0.08439869
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1784.6, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.005124665 0.014335622
## sample estimates:
## p
## 0.008648649
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.15 0.43
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1832, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0006928545 0.0059315037
## sample estimates:
## p
## 0.002162162
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.08
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.03 0.23
#################################
##########Specific phobia##########
#################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Specific phobias", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.82 0.10 0.08
KODAP_data_complete_specificphobia <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD2_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD3_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD4_pre_recode %in% c("F40.2 Spezifische Phobie") |
KODAP_data_complete$ICD5_pre_recode %in% c("F40.2 Spezifische Phobie"),]
length(KODAP_data_complete_specificphobia$Patient_ID)
## [1] 703
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_specificphobia$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_specificphobia$Patient_ID)
Observation
## [1] 678 22 3
round(Observation/length(KODAP_data_complete_specificphobia$Patient_ID)*100,1)
## [1] 96.4 3.1 0.4
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 104.6, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.290104e-32
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.75807e-12
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.106364e-20
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.18116165 0.30071174 0.05373547
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 615.88, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02018695 0.04777189
## sample estimates:
## p
## 0.03129445
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.3
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.19 0.46
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 689.07, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.001102765 0.013513634
## sample estimates:
## p
## 0.004267425
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.17
################################################
##########Generalized Anxiety Disorder##########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "GAD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.87 0.07 0.06
KODAP_data_complete_GAD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F41.1 Generalisierte Angststörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F41.1 Generalisierte Angststörung"),]
length(KODAP_data_complete_GAD$Patient_ID)
## [1] 552
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_GAD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_GAD$Patient_ID)
Observation
## [1] 526 20 6
round(Observation/length(KODAP_data_complete_GAD$Patient_ID)*100,1)
## [1] 95.3 3.6 1.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 35.361, df = 2, p-value = 2.096e-08
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 3.100055e-10
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.0009535313
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 1.546598e-07
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0958392 0.4897355 0.1925285
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 473.05, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.02285853 0.05637906
## sample estimates:
## p
## 0.03623188
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.49
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.31 0.76
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 526.31, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004426108 0.024731112
## sample estimates:
## p
## 0.01086957
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.19
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.08 0.44
################################################
##########Obsessive compulsive disorders########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "OCD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.93 0.04 0.03
KODAP_data_complete_OCD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F42.X Zwangsstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F42.X Zwangsstörung"),]
length(KODAP_data_complete_OCD$Patient_ID)
## [1] 791
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_OCD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_OCD$Patient_ID)
Observation
## [1] 778 11 2
round(Observation/length(KODAP_data_complete_OCD$Patient_ID)*100,1)
## [1] 98.4 1.4 0.3
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 36.12, df = 2, p-value = 1.435e-08
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.298215e-11
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 0.0001091024
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.469058e-08
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.05799452 0.34852567 0.08303939
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 745.67, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.007329893 0.025530476
## sample estimates:
## p
## 0.01390645
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.35
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.18 0.64
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 781.03, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0004380695 0.0101435327
## sample estimates:
## p
## 0.002528445
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.08
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.01 0.33
################################################
##########Post traumatic stress disorder########
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "PTSD", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.82 0.10 0.08
KODAP_data_complete_PTSD <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F43.1 Posttraumatische Belastungsstörung"),]
length(KODAP_data_complete_PTSD$Patient_ID)
## [1] 1067
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_PTSD$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_PTSD$Patient_ID)
Observation
## [1] 1052 13 2
round(Observation/length(KODAP_data_complete_PTSD$Patient_ID)*100,1)
## [1] 98.6 1.2 0.2
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 205.77, df = 2, p-value < 2.2e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.22548e-70
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.63473e-33
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 7.623017e-35
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.20836735 0.11670062 0.02352729
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 1013.7, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.006788272 0.021319397
## sample estimates:
## p
## 0.01218369
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.12
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.07 0.20
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1057, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0003247314 0.0075301326
## sample estimates:
## p
## 0.001874414
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.02
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.09
################################################
##########Any somatoform Disorders##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Any somatoform disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.86 0.08 0.06
KODAP_data_complete_Somatoform <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F45.X Somatoforme Störungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F45.X Somatoforme Störungen"),]
length(KODAP_data_complete_Somatoform$Patient_ID)
## [1] 1074
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Somatoform$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Somatoform$Patient_ID)
Observation
## [1] 1009 48 17
round(Observation/length(KODAP_data_complete_Somatoform$Patient_ID)*100,1)
## [1] 93.9 4.5 1.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 56.955, df = 2, p-value = 4.29e-13
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.534682e-15
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 5.407048e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 7.536937e-12
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0890947 0.5735931 0.2662096
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 888.76, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.03347037 0.05928157
## sample estimates:
## p
## 0.04469274
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.57
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.43 0.76
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 1005.1, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.009547387 0.025770512
## sample estimates:
## p
## 0.01582868
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.27
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.16 0.43
################################################
##########Somatization disorder##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Somatization disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.78 0.13 0.10
KODAP_data_complete_Somatization <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD2_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD3_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD4_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10") |
KODAP_data_complete$ICD5_pre_clean %in% c("F45.0","F45.00", "F45.1", "F45.10"),]
length(KODAP_data_complete_Somatization$Patient_ID)
## [1] 211
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Somatization$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Somatization$Patient_ID)
Observation
## [1] 203 7 1
round(Observation/length(KODAP_data_complete_Somatization$Patient_ID)*100,1)
## [1] 96.2 3.3 0.5
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 42.653, df = 2, p-value = 5.47e-10
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.155877e-13
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.156523e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 5.203577e-08
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.2402898 0.2607680 0.0488167
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 182.07, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01461394 0.06996360
## sample estimates:
## p
## 0.03317536
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.26
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.11 0.55
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 205.04, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0002474437 0.0302007408
## sample estimates:
## p
## 0.004739336
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.05
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.31
################################################
##########Pain disorder##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Pain disorder", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.88 0.07 0.05
KODAP_data_complete_Pain <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD2_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD3_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD4_pre_clean %in% c("F45.4","F45.40", "F45.41") |
KODAP_data_complete$ICD5_pre_clean %in% c("F45.4","F45.40", "F45.41"),]
length(KODAP_data_complete_Pain$Patient_ID)
## [1] 508
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Pain$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Pain$Patient_ID)
Observation
## [1] 465 30 13
round(Observation/length(KODAP_data_complete_Pain$Patient_ID)*100,1)
## [1] 91.5 5.9 2.6
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 7.0277, df = 2, p-value = 0.02978
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 0.07927109
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.775826
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 0.02398158
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.035381 0.898171 0.510027
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 393.32, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.04085658 0.08418493
## sample estimates:
## p
## 0.05905512
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.9
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.62 1.28
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 455.44, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01428679 0.04450754
## sample estimates:
## p
## 0.02559055
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.51
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.28 0.89
################################################
##########Eating disorders##################
################################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Eating disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.91 0.05 0.04
KODAP_data_complete_Eating <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD2_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD3_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD4_pre_recode %in% c("F50.X Essstörung") |
KODAP_data_complete$ICD5_pre_recode %in% c("F50.X Essstörung"),]
length(KODAP_data_complete_Eating$Patient_ID)
## [1] 857
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Eating$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Eating$Patient_ID)
Observation
## [1] 849 8
Observation[3] <- 0
Observation
## [1] 849 8 0
round(Observation/length(KODAP_data_complete_Eating$Patient_ID)*100,1)
## [1] 99.1 0.9 0.0
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 70.355, df = 2, p-value = 5.281e-16
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 6.865318e-25
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 4.926831e-11
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 4.119904e-15
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.0905979 0.1796162 0.0000000
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 823.34, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.004346906 0.019076925
## sample estimates:
## p
## 0.009334889
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.18
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.08 0.37
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 855, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.000000000 0.005563187
## sample estimates:
## p
## 0
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.14
#########################################
##########Substance-use disorders########
#########################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Substance use disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.90 0.06 0.04
KODAP_data_complete_SubstanceUse <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F1X.X Psychische und Verhaltensstörungen durch psychotrope Substanzen"),]
length(KODAP_data_complete_SubstanceUse$Patient_ID)
## [1] 764
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_SubstanceUse$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_SubstanceUse$Patient_ID)
Observation
## [1] 748 15 1
round(Observation/length(KODAP_data_complete_SubstanceUse$Patient_ID)*100,1)
## [1] 97.9 2.0 0.1
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 55.102, df = 2, p-value = 1.083e-12
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 2.32986e-17
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.982076e-06
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 3.457945e-13
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.08808815 0.34545660 0.03017966
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 703.26, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.01143871 0.03294463
## sample estimates:
## p
## 0.01963351
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.35
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.20 0.58
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 758.01, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 6.832858e-05 8.456433e-03
## sample estimates:
## p
## 0.001308901
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.03
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.19
#########################################
##########Psychotic disorders############
#########################################
prevalence_1834 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "1834y"])
prevalence_3549 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "3549y"])
prevalence_5064 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "5064y"])
prevalence_1864 <- (census_amount_1834/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_1834+
(census_amount_3549/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_3549+
(census_amount_5064/sum(census_amount_1834,census_amount_3549, census_amount_5064))*prevalence_5064
prevalence_6574 <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "6574y"])
prevalence_75plus <- as.numeric(Prevalence_estimates[Prevalence_estimates$Diagnosis == "Psychotic disorders", "75yplus"])
#Ratios in reference population
expected_ratio_1864 <- (census_amount_1864_LTC*prevalence_1864)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_6574 <- (census_amount_6574_LTC*prevalence_6574)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratio_75plus <- (census_amount_75plus_LTC*prevalence_75plus)/((census_amount_1864_LTC*prevalence_1864)+(census_amount_6574_LTC*prevalence_6574)+(census_amount_75plus_LTC*prevalence_75plus))
expected_ratios <- c(expected_ratio_1864,
expected_ratio_6574,
expected_ratio_75plus)
round(expected_ratios,2)
## [1] 0.89 0.06 0.05
KODAP_data_complete_Psychotic <- KODAP_data_complete[KODAP_data_complete$ICD1_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD2_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD3_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD4_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen") |
KODAP_data_complete$ICD5_pre_recode %in% c("F20.X Schizophrenie",
"F21 F22 F23 F24 F28 F29 Psychotische oder wahnhafte Störungen (außer Schizophrenie)",
"F25.X Schizoaffektive Störungen"),]
length(KODAP_data_complete_Psychotic$Patient_ID)
## [1] 336
#Observed vs. expected:
Observation <- as.vector(table(KODAP_data_complete_Psychotic$Age_Stepped))
Expected <- expected_ratios*length(KODAP_data_complete_Psychotic$Patient_ID)
Observation
## [1] 331 4 1
round(Observation/length(KODAP_data_complete_Psychotic$Patient_ID)*100,1)
## [1] 98.5 1.2 0.3
# Chi-squared test for given probabilities
test <- chisq.test(Observation, p = expected_ratios)
test
##
## Chi-squared test for given probabilities
##
## data: Observation
## X-squared = 32.724, df = 2, p-value = 7.834e-08
# Post-hoc binomial-test for each category with Bonferroni-correction
binom.test(Observation[1], sum(Observation), expected_ratios[1])$p.value*3
## [1] 1.819468e-11
binom.test(Observation[2], sum(Observation), expected_ratios[2])$p.value*3
## [1] 1.773712e-05
binom.test(Observation[3], sum(Observation), expected_ratios[3])$p.value*3
## [1] 4.828575e-06
#Estimating underrepresentation compared to reference population
#Representation quotients
Observation/Expected
## [1] 1.11155865 0.18452267 0.06045077
#Confidence-intervals of Representation quotients
#Confidence-intervals around sample proportion
prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[2] out of sum(Observation), null probability 0.5
## X-squared = 318.24, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.003820372 0.032295397
## sample estimates:
## p
## 0.01190476
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_6574,2)
## p
## 0.18
round(as.vector(prop.test(x = Observation[2], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_6574,2)
## [1] 0.06 0.50
#Confidence-intervals around sample proportion
prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)
##
## 1-sample proportions test with continuity correction
##
## data: Observation[3] out of sum(Observation), null probability 0.5
## X-squared = 330.03, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.0001553772 0.0190996535
## sample estimates:
## p
## 0.00297619
#Confidence-intervals around sample proportion relative to expected proportion
round(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$estimate/expected_ratio_75plus,2)
## p
## 0.06
round(as.vector(prop.test(x = Observation[3], n = sum(Observation), conf.level = .95)$conf.int)/expected_ratio_75plus,2)
## [1] 0.00 0.39