#Packages used
library(haven)
library(tidyverse)
library(ggpubr)
library(scales)
#Prep Data
selects <- read_dta("495_Selects_CumulativeFile_Data_1971-2019_v2.2.0.dta")
selects.short <- selects %>% select(year, age,sex, lr1,vdn1b,ip13, ip14) %>%
filter(year >= 2018) %>%
filter(lr1 >= 0) %>%
filter(ip13 >= 1) %>%
filter(ip14 >=0) %>%
filter(age > 0)
#2018 gender gap visualization
group.df <- selects.short %>% group_by(age,sex) %>% summarise(mean_lr = mean(lr1))
ggplot(data=group.df, aes(x=(age), y=(mean_lr),colour= as.factor(sex)))+
geom_point(alpha = 0.5)+
geom_smooth()+
scale_color_manual(values=c("blue","#eb7e83"), labels= c("Männer","Frauen"))+
theme(legend.title = element_blank())+
labs(title = "2018 wählten junge Frauen linker als gleichaltrige Männer.",
subtitle = "Selbstpositionierung von Frauen und Männern nach Alter, 0 = links, 10 = rechts", y= "links-rechts",x= "Age")
#1971 gender gap visualization
selects.old.gg <- selects %>% select(year, age,sex, lr1,vdn1b,ip13) %>%
filter(year == 1971) %>%
mutate(geschlecht = case_when(sex <=0 ~ "Mann",
sex == 1 & age %in% seq(18,50) ~ "F18-50",
TRUE ~ "F51+")) %>%
filter(lr1 >= 0) %>%
filter(age >0)
group.df <- selects.old.gg %>% group_by(age,sex) %>% summarise(mean_lr = mean(lr1))
ggplot(data=group.df, aes(x=(age), y=(mean_lr),colour= as.factor(sex)))+
geom_point(alpha = 0.5)+
geom_smooth()+
scale_color_manual(values=c("blue","#eb7e83"), labels= c("Männer","Frauen"))+
theme(legend.title = element_blank())+
labs(title = "1971 wählten die Frauen nicht linker als die Männer. Ältere Frauen wählten sogar konservativer.",
subtitle = "Selbstpositionierung von Frauen und Männern nach Alter, 0 = links, 10 = rechts", y= "links-rechts",x= "Alter")
#Umweltschutz Visualisierung
group.nature <- selects.short %>% group_by(age,sex) %>% summarise(mean_ip14 = mean(ip14))
ggplot(data=group.nature, aes(x=(age), y=(mean_ip14),colour= as.factor(sex)))+
geom_point(alpha = 0.5)+
geom_smooth(method = "loess")+
scale_color_manual(values=c("blue","#eb7e83"), labels= c("Männer","Frauen"))+
theme(legend.title = element_blank())+
labs(title = "Junge Frauen priotisieren den Umweltschutz verstärkter als gleichaltrige Männer",
subtitle = "Selbstpositionierung Umwelt vs. Wirtschaft: 1 = für Umweltschutz & 5 = für Wirtschaftswahstum", x= "Alter", y= "Umwelt - Wirtschaft")
selects.mip.young <- selects %>%
select(year, age,sex, lr1, mip1) %>%
filter(year >= 2018) %>% filter(lr1 >= 0) %>%
filter(mip1 >= 0) %>%
filter(age>0) %>%
filter(sex == 1) %>%
filter(age <= 50)
selects.mip.old <- selects %>%
select(year, age,sex, lr1, mip1) %>%
filter(year >= 2018) %>% filter(lr1 >= 0) %>%
filter(mip1 >= 0) %>%
filter(age>0) %>%
filter(sex == 1) %>%
filter(age > 50)
tr2.young <- selects.mip.young %>% group_by(mip1) %>%
summarise(n=n()) %>% mutate(percentage = (n/sum(n))*100)
tr2.old <- selects.mip.old %>% group_by(mip1) %>%
summarise(n=n()) %>% mutate(percentage= (n/sum(n))*100)
tr2.young$topics <- as.factor(tr2.young$mip1)
tr2.old$topics <- as.factor(tr2.old$mip1)
tr2.young$topics <- recode_factor(tr2.young$topics,"1"= "agriculture",
"2"= "economics",
"3"= "education.youth.culture",
"4" = "Umwelt und Energie",
"5" = "Europäische Integration",
"6"="finances.taxes",
"7"="gender issues.discrimination",
"8"="Immigration und Asylfragen",
"9"="international relations.army",
"10"= "labour market",
"11"= "Law and order",
"12"= "Politisches System",
"13"="Gesundheit",
"14"= "public service",
"15"= "regions.national cohesion",
"16"= "Soziale Sicherheit",
"17"= "other problem",
"18"="no problem"
)
tr2.old$topics <- recode_factor(tr2.old$topics,"1"= "agriculture",
"2"= "economics",
"3"= "education.youth.culture",
"4" = "Umwelt und Energie",
"5" = "Europäische Integration",
"6"="finances.taxes",
"7"="gender issues.discrimination",
"8"="Immigration und Asylfragen",
"9"="international relations.army",
"10"= "labour market",
"11"= "Law and order",
"12"= "Politisches System",
"13"="Gesundheit",
"14"= "public service",
"15"= "regions.national cohesion",
"16"= "Soziale Sicherheit",
"17"= "other problem",
"18"="no problem"
)
summary(tr2.young$topics) # All 18 topics
## agriculture economics
## 1 1
## education.youth.culture Umwelt und Energie
## 1 1
## Europäische Integration finances.taxes
## 1 1
## gender issues.discrimination Immigration und Asylfragen
## 1 1
## international relations.army labour market
## 1 1
## Law and order Politisches System
## 1 1
## Gesundheit public service
## 1 1
## regions.national cohesion Soziale Sicherheit
## 1 1
## other problem no problem
## 1 1
short.tr2.young <- tr2.young[order(desc(tr2.young$percentage)),] %>% head()
short.tr2.old <- tr2.old[order(desc(tr2.old$percentage)),] %>% head()
#Plot young women
ggplot(short.tr2.young, aes(x=reorder(topics, percentage), y=percentage))+
geom_col(width = .7, fill= c("#8b1a22","#eb7e83","#edb81d","#947032","#565b7b","#86b0a6"))+
theme(axis.text.x = element_text(size = 12), axis.text.y = element_text(size = 12))+
coord_flip()+
ylim(0,32)+
scale_y_continuous(labels = scales::percent_format(scale = 1))+
labs(x="", y="", subtitle = "Frauen bis und mit 50", title = "Die 6 meistgenannten Themen")
#Plot older women
ggplot(short.tr2.old, aes(x=reorder(topics, percentage), y=percentage))+
geom_col(width = .7, fill= c("#8b1a22","#eb7e83","#565b7b","#edb81d","#947032","#86b0a6"))+
theme(axis.text.x = element_text(size = 12), axis.text.y = element_text(size = 12))+
coord_flip()+
ylim(0,32)+
scale_y_continuous(labels = scales::percent_format(scale = 1))+
labs(x="", y="", subtitle = "Frauen über 50", title = "")
