### Libraries ------------------------------------------------------------------ library(ggplot2) library(cowplot) library(RColorBrewer) library(reshape2) library(forcats) library(knitr) library(kableExtra) library(rlang) library(wesanderson) library(haven) library(margins)# library(broom) library(stargazer) library(scales) library(dplyr) library(tidyr) detach(package:mfx) detach(package:MASS) # Read data -------------------------------- a<-readRDS("est.RDS") #### first descriptive based on reasons #### table((a$mreason_lang), useNA = "always") a<-a %>% mutate(mreas_na=ifelse(a$mreason_lang=="No answer", TRUE, FALSE)) table(a$country, a$mreas_na) a <- a %>% filter(!is.na(reason_move_prof) | !is.na(reason_move_other)) a %>% group_by(country) %>% summarise(mean_na=mean(mreas_na)) a<-a %>% mutate(no_reas=reason_stud+reason_comp+reason_trade+reason_cust+reason_inc+ reason_requ+reason_lab+ reason_partner+reason_soc+reason_move_prof+reason_move_other+reason_holi+reason_cult+reason_inter) d<-a %>% group_by(country,mreas_na) %>% summarise(mean_na=mean(no_reas)) %>% ungroup a<-a %>% select(-reason_stud,-reason_comp,-reason_trade,-reason_cust,-reason_inc,- reason_requ,-reason_lab,- reason_partner,-reason_soc,-reason_move_prof,-reason_move_other,-reason_holi,-reason_cult,-reason_inter) #### Prepare for estimations ##### est<-a #1. type logit (max and min sample x stepwise introduction X aggregate) #2. type logit (max and min sample x stepwise introduction X country_wise) #1. langjob logit (max and min sample x stepwise introduction X aggregate) #2. langjob logit (max and min sample x stepwise introduction X country_wise) #2. part (ref cat part=0) est <- within(est, part <- relevel(factor(part), ref = "0")) # part=0 no partner # part=1 partner with German native language # part=2 partner with other native language #3. Degree (ref cat part=2) est <- within(est, degree <- relevel(factor(degree), ref = "2")) # 0 No degree # 1 School leaving certificate which cannot lead to higher education # 2 School leaving certificate which can lead to higher education # 3 University degree # 4 PhD stargazer(est, type="text") #Aggregate 0+1 and 3+4 est<-est %>% mutate(degree2=case_when(is.na(.$degree) ~ NA, .$degree =="0" ~ FALSE, .$degree =="1" ~ FALSE, .$degree =="2" ~ FALSE, .$degree =="3" ~ TRUE, .$degree =="4" ~ TRUE, .$degree =="5" ~ FALSE), degree=degree2) table(est$degree, est$degree2, useNA = "always") table(est$mreas_na) gi<-est #### estimations #### library(MASS) #MASS:: select clashes with dplyr::select, load late library(mfx) library(lmtest) library(sandwich) mreas_na_full_fe<-as.formula("mreas_na ~ no_reas+factor(age)+female+children_d_na+part+occupationac+degree+risk+patient+english+country") mreas_na_full<-as.formula("mreas_na ~ no_reas+factor(age)+female+children_d_na+part+occupationac+degree+risk+patient+english") TOT<-probitmfx(formula = mreas_na_full_fe, data=gi, atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) BIH<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="BIH",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) CZE<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="CZE",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) ESP<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="ESP",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) GBR<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="GBR",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) ITA<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="ITA",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) JPN<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="JPN",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) KOR<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="KOR",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) NLD<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="NLD",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) POL<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="POL",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) ROU<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="ROU",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) IND<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="IND",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) IDN<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="IDN",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) UKR<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="UKR",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) MEX<-probitmfx(formula = mreas_na_full, data=gi[gi$country=="MEX",], atmean = FALSE, robust = TRUE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, control = list()) stargazer(TOT$fit, BIH$fit, CZE$fit, ESP$fit, GBR$fit, ITA$fit, JPN$fit, KOR$fit, NLD$fit, POL$fit, ROU$fit, IND$fit, IDN$fit, UKR$fit, MEX$fit, coef = list(TOT$mfxest[,1], BIH$mfxest[,1], CZE$mfxest[,1], ESP$mfxest[,1], GBR$mfxest[,1], ITA$mfxest[,1], JPN$mfxest[,1], KOR$mfxest[,1], NLD$mfxest[,1], POL$mfxest[,1], ROU$mfxest[,1], IND$mfxest[,1], IDN$mfxest[,1], UKR$mfxest[,1], MEX$mfxest[,1]), se = list(TOT$mfxest[,2], BIH$mfxest[,2], CZE$mfxest[,2], ESP$mfxest[,2], GBR$mfxest[,2], ITA$mfxest[,2], JPN$mfxest[,2], KOR$mfxest[,2], NLD$mfxest[,2], POL$mfxest[,2], ROU$mfxest[,2], IND$mfxest[,2], IDN$mfxest[,2], UKR$mfxest[,2], MEX$mfxest[,2]), column.labels = c("TOT", "BIH", "CZE", "ESP", "GBR", "ITA", "JPN", "KOR", "NLD", "POL", "ROU", "IND", "IDN", "UKR", "MEX"), header=FALSE, style="default", dep.var.labels = "main reason NA", covariate.labels= c("Number of reasons", "Age: under 35 years", "Gender: female", "Gender: n/a", "Children", "Partner (native German)", "Partner (other native)", "Occ.: high appl./low comm. skills", "Occ.: high appl./high comm. skills", "Occ.: in education", "Occ.: other occ./no answer", "University degree", "Risk attitude", "Patience", "English speaker"), nobs=TRUE, align=TRUE, no.space=TRUE, single.row=TRUE, model.names = FALSE, omit = c("Constant", "country"), font.size = "small", add.lines = list(c("Fixed effects?", "Yes", "No", "No","No","No","No","No","No","No","No","No","No","No","No","No")), notes= "Average marginal effects. Heteroscedasticity robust White standard errors in parentheses.", omit.stat = c("aic", "ll"), out = "tables/mrea_na_country_ame.txt") TOT_type<-tidy(TOT) %>% filter(term != "(Intercept)") %>% mutate(model = "Total") BIH_type<-tidy(BIH) %>% filter(term != "(Intercept)") %>% mutate(model = "BIH (n=158)") CZE_type<-tidy(CZE) %>% filter(term != "(Intercept)") %>% mutate(model = "CZE (n=417)") ESP_type<-tidy(ESP) %>% filter(term != "(Intercept)") %>% mutate(model = "ESP (n=567)") GBR_type<-tidy(GBR) %>% filter(term != "(Intercept)") %>% mutate(model = "GBR (n=399)") ITA_type<-tidy(ITA) %>% filter(term != "(Intercept)") %>% mutate(model = "ITA (n=298)") JPN_type<-tidy(JPN) %>% filter(term != "(Intercept)") %>% mutate(model = "JPN (n=252)") KOR_type<-tidy(KOR) %>% filter(term != "(Intercept)") %>% mutate(model = "KOR (n=456)") NLD_type<-tidy(NLD) %>% filter(term != "(Intercept)") %>% mutate(model = "NLD (n=121)") POL_type<-tidy(POL) %>% filter(term != "(Intercept)") %>% mutate(model = "POL (n=182)") ROU_type<-tidy(ROU) %>% filter(term != "(Intercept)") %>% mutate(model = "ROU (n=296)") IND_type<-tidy(IND) %>% filter(term != "(Intercept)") %>% mutate(model = "IND (n=762)") IDN_type<-tidy(IDN) %>% filter(term != "(Intercept)") %>% mutate(model = "IDN (n=819)") UKR_type<-tidy(UKR) %>% filter(term != "(Intercept)") %>% mutate(model = "UKR (n=726)") MEX_type<-tidy(MEX) %>% filter(term != "(Intercept)") %>% mutate(model = "MEX (n=451)") gi %>% count(country) %>% arrange(-n) country_l_type<-rbind(TOT_type, ESP_type, GBR_type, CZE_type, ITA_type, POL_type, ROU_type, NLD_type, BIH_type, UKR_type, MEX_type, IND_type, IDN_type, KOR_type, JPN_type) country_l_type<-country_l_type %>% mutate(sign=ifelse(model=="Total" & p.value<0.05, TRUE, FALSE)) %>% group_by(term) %>% mutate(sign_5=max(sign), sign=ifelse(sign_5==0, "P>0.05 (aggr. model)", "P<0.05 (aggr. model)"), sign=as.factor(sign)) %>% filter(model!="Total") library(dotwhisker) library(ggsci) p_country1<-dwplot(subset(country_l_type, (country_l_type$term=="no_reas" | country_l_type$term=="typeTRUE" | country_l_type$term=="factor(age)TRUE" | country_l_type$term=="female1" | country_l_type$term=="children_d_naTRUE" | country_l_type$term=="part1" | country_l_type$term=="part2" | country_l_type$term=="occupationac1" | country_l_type$term=="occupationac2" | country_l_type$term=="occupationac3" | country_l_type$term=="degreeTRUE" | country_l_type$term=="risk" | country_l_type$term=="patient" | country_l_type$term=="englishTRUE" )), vline = geom_vline(xintercept = 0, colour = "grey60", linetype = 2), dodge_size= 0.7, dot_args = list(aes(shape =as.factor(sign)), size=4)) + scale_x_continuous(limits = c(-0.7, 0.7))+ scale_y_discrete( labels=c( no_reas= "Number of reasons", "factor(age)TRUE" = "Age: under 35 years", female1 = "Gender: female", children_d_naTRUE = "Children", "part1" = "Partner (native German)", "part2" = "Partner (other native)", degreeTRUE= "University degree", "occupationac1" = "Occ.: high appl./low comm. skills", "occupationac2" = "Occ.: high appl./high comm. skills", "occupationac3" = "Occ.: in education", risk = "Risk attitude", patient = "Patience", "englishTRUE" = "English speaker" ))+ xlab("AME")+ theme(legend.title = element_blank()) pdf("mreas_na_country1.pdf", paper="a4r", width = 12, height = 14) p_country1 dev.off() ##### many NAs (NLD, KOR, IND, MEX) #### table(gi$mreas_na, gi$country, useNA = "always") country_l_type<-rbind(TOT_type, NLD_type, MEX_type, IND_type, KOR_type) country_l_type<-country_l_type %>% mutate(sign=ifelse(model=="Total" & p.value<0.05, TRUE, FALSE)) %>% group_by(term) %>% mutate(sign_5=max(sign), sign=ifelse(sign_5==0, "P>0.05 (aggr. model)", "P<0.05 (aggr. model)"), sign=as.factor(sign)) %>% filter(model!="Total") p_country1<-dwplot(subset(country_l_type, (country_l_type$term=="no_reas" | country_l_type$term=="typeTRUE" | country_l_type$term=="factor(age)TRUE" | country_l_type$term=="female1" | country_l_type$term=="children_d_naTRUE" | country_l_type$term=="part1" | country_l_type$term=="part2" | country_l_type$term=="occupationac1" | country_l_type$term=="occupationac2" | country_l_type$term=="occupationac3" | country_l_type$term=="degreeTRUE" | country_l_type$term=="risk" | country_l_type$term=="patient" | country_l_type$term=="englishTRUE" )), vline = geom_vline(xintercept = 0, colour = "grey60", linetype = 2), dodge_size= 0.7, dot_args = list(aes(shape =as.factor(sign)), size=4)) + scale_x_continuous(limits = c(-0.7, 0.7))+ scale_y_discrete( labels=c( no_reas= "Number of reasons", "factor(age)TRUE" = "Age: under 35 years", female1 = "Gender: female", children_d_naTRUE = "Children", "part1" = "Partner (native German)", "part2" = "Partner (other native)", degreeTRUE= "University degree", "occupationac1" = "Occ.: high appl./low comm. skills", "occupationac2" = "Occ.: high appl./high comm. skills", "occupationac3" = "Occ.: in education", risk = "Risk attitude", patient = "Patience", "englishTRUE" = "English speaker" ))+ xlab("AME")+ theme(legend.title = element_blank()) pdf("mreas_na_country_many1.pdf", paper="a4r", width = 12, height = 14) p_country1 dev.off() #### few NAs #### country_l_type<-rbind(TOT_type, ESP_type, GBR_type, CZE_type, ITA_type, POL_type, ROU_type, BIH_type, UKR_type, IDN_type, JPN_type) country_l_type<-country_l_type %>% mutate(sign=ifelse(model=="Total" & p.value<0.05, TRUE, FALSE)) %>% group_by(term) %>% mutate(sign_5=max(sign), sign=ifelse(sign_5==0, "P>0.05 (aggr. model)", "P<0.05 (aggr. model)"), sign=as.factor(sign)) %>% filter(model!="Total") p_country1<-dwplot(subset(country_l_type, (country_l_type$term=="no_reas" | country_l_type$term=="typeTRUE" | country_l_type$term=="factor(age)TRUE" | country_l_type$term=="female1" | country_l_type$term=="children_d_naTRUE" | country_l_type$term=="part1" | country_l_type$term=="part2" | country_l_type$term=="occupationac1" | country_l_type$term=="occupationac2" | country_l_type$term=="occupationac3" | country_l_type$term=="degreeTRUE" | country_l_type$term=="risk" | country_l_type$term=="patient" | country_l_type$term=="englishTRUE" )), vline = geom_vline(xintercept = 0, colour = "grey60", linetype = 2), dodge_size= 0.7, dot_args = list(aes(shape =as.factor(sign)), size=4)) + scale_x_continuous(limits = c(-0.7, 0.7))+ scale_y_discrete( labels=c( no_reas= "Number of reasons", "factor(age)TRUE" = "Age: under 35 years", female1 = "Gender: female", children_d_naTRUE = "Children", "part1" = "Partner (native German)", "part2" = "Partner (other native)", degreeTRUE= "University degree", "occupationac1" = "Occ.: high appl./low comm. skills", "occupationac2" = "Occ.: high appl./high comm. skills", "occupationac3" = "Occ.: in education", risk = "Risk attitude", patient = "Patience", "englishTRUE" = "English speaker" ))+ xlab("AME")+ theme(legend.title = element_blank()) pdf("mreas_na_country_few1.pdf", paper="a4r", width = 12, height = 14) p_country1 dev.off()