Miscellaneous
Julia Rohrer
2026-06-15
On this page are some additional checks, concerning migration background, that lead to remarks made in the manuscript (without being presented as central analysis results).
Let’s check some migration numbers
These are just to check whether our mapping goes wrong as predicted, see Footnote 3 in the manuscript. We are using numbers received via the Einwohnermeldeamt.
load("prep.RData")
library(binom)
prop.table(table(combined_all_schooltypes$german_at_home[combined_all_schooltypes$year == 2010])) # 91%## numeric(0)prop.table(table(combined_all_schooltypes$german_at_home[combined_all_schooltypes$year == 2015])) # 91%## numeric(0)prop.table(table(combined_all_schooltypes$german_at_home[combined_all_schooltypes$year == 2023])) # 88%## numeric(0)ewo <- readRDS("Files/Ewo_PLZ_Geschl_Migration.rds")
ewo <- ewo[ewo$Alter >= 12 & ewo$Alter <= 18,]
table(ewo$Zuwanderungshintergrund)##
## Ausländer
## 1271
## Aussiedler
## 840
## Einbürgerung
## 1156
## einseitiger elterlicher Zuwanderungshintergrund
## 567
## ohne (erkennbaren) Zuwanderungshintergrund
## 1451
## persönl. Zuwanderungshintergrund aber Eltern ohne
## 803total <- sum(ewo$Anzahl)
sum(ewo$Anzahl[ewo$Zuwanderungshintergrund == "Ausländer"])/total # 12%## [1] 0.1216921sum(ewo$Anzahl[ewo$Zuwanderungshintergrund == "Aussiedler"])/total # 2%## [1] 0.02168009sum(ewo$Anzahl[ewo$Zuwanderungshintergrund == "Einbürgerung"])/total # 6%## [1] 0.05757721sum(ewo$Anzahl[ewo$Zuwanderungshintergrund == "einseitiger elterlicher Zuwanderungshintergrund"])/total # 01%## [1] 0.01121259sum(ewo$Anzahl[ewo$Zuwanderungshintergrund == "ohne (erkennbaren) Zuwanderungshintergrund"])/total # 77%## [1] 0.7705324sum(ewo$Anzahl[ewo$Zuwanderungshintergrund == "persönl. Zuwanderungshintergrund aber Eltern ohne"])/total # 2%## [1] 0.01730561ewo$german_at_home <- NA
ewo$german_at_home[ewo$Zuwanderungshintergrund == "Ausländer"] <- 0
ewo$german_at_home[ewo$Zuwanderungshintergrund == "Einbürgerung"] <- 0
ewo$german_at_home[ewo$Zuwanderungshintergrund == "Aussiedler"] <- 1
ewo$german_at_home[ewo$Zuwanderungshintergrund == "einseitiger elterlicher Zuwanderungshintergrund"] <- 1
ewo$german_at_home[ewo$Zuwanderungshintergrund == "ohne (erkennbaren) Zuwanderungshintergrund"] <- 1
ewo$german_at_home[ewo$Zuwanderungshintergrund == "persönl. Zuwanderungshintergrund aber Eltern ohne"] <- 1
sum(ewo$Anzahl[ewo$Jahr == 2010 & ewo$german_at_home == 1])/sum(ewo$Anzahl[ewo$Jahr == 2010]) # 89.9%## [1] 0.8993833sum(ewo$Anzahl[ewo$Jahr == 2015 & ewo$german_at_home == 1])/sum(ewo$Anzahl[ewo$Jahr == 2015]) # 85%## [1] 0.8534373sum(ewo$Anzahl[ewo$Jahr == 2023 & ewo$german_at_home == 1])/sum(ewo$Anzahl[ewo$Jahr == 2023]) # 75%## [1] 0.75498# Let's do by age, gender, and year -- in the sample versus in the population
# Fold in confidence interval
comp_ewo <- data.frame(matrix(NA, nrow = 7*3, ncol = 10))
names(comp_ewo) <- c("year", "age", "german_girls", "german_girls_lb", "german_girls_ub","german_girls_ewo",
"german_boys", "german_boys_lb", "german_boys_ub", "german_boys_ewo")
comp_ewo$year <- rep(c(2010, 2015, 2023), each = 7)
comp_ewo$age <- rep(12:18, times = 3)
n_temp <- NA
sum_temp <- NA
for (i in 1:nrow(comp_ewo)) {
print(i)
# In the data
# girls, mean
comp_ewo$german_girls[i] <- mean(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age == comp_ewo$age[i] &
combined_all_schooltypes$gender == "female" &
combined_all_schooltypes$year == comp_ewo$year[i]],
na.rm = TRUE)
# girls, CI
n_temp <- sum(!is.na(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age == comp_ewo$age[i] &
combined_all_schooltypes$gender == "female" &
combined_all_schooltypes$year == comp_ewo$year[i]]))
sum_temp <- sum(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age == comp_ewo$age[i] &
combined_all_schooltypes$gender == "female" &
combined_all_schooltypes$year == comp_ewo$year[i]],
na.rm = TRUE)
comp_ewo[i, c("german_girls_lb", "german_girls_ub")] <- binom.confint(sum_temp, n_temp, conf.level = .95, methods = "wilson")[, c("lower", "upper")]
# boys, mean
comp_ewo$german_boys[i] <- mean(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age == comp_ewo$age[i] &
combined_all_schooltypes$gender == "male" &
combined_all_schooltypes$year == comp_ewo$year[i]],
na.rm = TRUE)
# boys, ci
n_temp <- sum(!is.na(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age == comp_ewo$age[i] &
combined_all_schooltypes$gender == "male" &
combined_all_schooltypes$year == comp_ewo$year[i]]))
sum_temp <- sum(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age == comp_ewo$age[i] &
combined_all_schooltypes$gender == "male" &
combined_all_schooltypes$year == comp_ewo$year[i]],
na.rm = TRUE)
comp_ewo[i, c("german_boys_lb", "german_boys_ub")] <- binom.confint(sum_temp, n_temp, conf.level = .95, methods = "wilson")[, c("lower", "upper")]
# In the city data
comp_ewo$german_girls_ewo[i] <- sum(ewo$Anzahl[ewo$Jahr == comp_ewo$year[i] &
ewo$Alter == comp_ewo$age[i] &
ewo$Geschlecht == "w" &
ewo$german_at_home == 1])/ # number of german speaking girls of that age in that year
sum(ewo$Anzahl[ewo$Jahr == comp_ewo$year[i] &
ewo$Alter == comp_ewo$age[i] &
ewo$Geschlecht == "w"]) # divided by total number of girls of that age in that year
comp_ewo$german_boys_ewo[i] <- sum(ewo$Anzahl[ewo$Jahr == comp_ewo$year[i] &
ewo$Alter == comp_ewo$age[i] &
ewo$Geschlecht == "m" &
ewo$german_at_home == 1])/ # number of german speaking boys of that age in that year
sum(ewo$Anzahl[ewo$Jahr == comp_ewo$year[i] &
ewo$Alter == comp_ewo$age[i] &
ewo$Geschlecht == "m"]) # divided by total number of boys of that age in that year
}## [1] 1## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 2## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 3## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 4## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 5## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 6## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 7## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 8## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 9## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 10## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 11## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 12## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 13## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 14## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 15## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 16## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 17## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 18## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 19## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 20## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA## [1] 21## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA
## Warning in
## mean.default(combined_all_schooltypes$german_at_home[combined_all_schooltypes$age
## == : argument is not numeric or logical: returning NA# Lets plot the comparison
# Dont forget: 2015 is a different type of assessment in the sample
library(ggplot2)
ggplot(data = comp_ewo[comp_ewo$year == 2010,], aes(x = age)) +
geom_point(aes(y = german_girls)) +
geom_line(aes(y = german_girls)) +
geom_ribbon(aes(ymin = german_girls_lb, ymax = german_girls_ub), alpha = .2) +
geom_point(aes(y = german_girls_ewo), color = "red") +
geom_line(aes(y = german_girls_ewo), color = "red") +
theme_minimal() +
coord_cartesian(ylim = c(.5, 1)) +
ggtitle("girls, 2010")## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_line()`).## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_ribbon()`).
ggplot(data = comp_ewo[comp_ewo$year == 2010,], aes(x = age)) +
geom_point(aes(y = german_boys)) +
geom_line(aes(y = german_boys)) +
geom_ribbon(aes(ymin = german_boys_lb, ymax = german_boys_ub), alpha = .2) +
geom_point(aes(y = german_boys_ewo), color = "red") +
geom_line(aes(y = german_boys_ewo), color = "red") +
theme_minimal() +
coord_cartesian(ylim = c(.5, 1)) +
ggtitle("boys, 2010")## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_line()`).## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_ribbon()`).
ggplot(data = comp_ewo[comp_ewo$year == 2015,], aes(x = age)) +
geom_point(aes(y = german_girls)) +
geom_line(aes(y = german_girls)) +
geom_ribbon(aes(ymin = german_girls_lb, ymax = german_girls_ub), alpha = .2) +
geom_point(aes(y = german_girls_ewo), color = "red") +
geom_line(aes(y = german_girls_ewo), color = "red") +
theme_minimal() +
coord_cartesian(ylim = c(.5, 1)) +
ggtitle("girls, 2015")## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_line()`).## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_ribbon()`).
ggplot(data = comp_ewo[comp_ewo$year == 2015,], aes(x = age)) +
geom_point(aes(y = german_boys)) +
geom_line(aes(y = german_boys)) +
geom_ribbon(aes(ymin = german_boys_lb, ymax = german_boys_ub), alpha = .2) +
geom_point(aes(y = german_boys_ewo), color = "red") +
geom_line(aes(y = german_boys_ewo), color = "red") +
theme_minimal() +
coord_cartesian(ylim = c(.5, 1)) +
ggtitle("boys, 2015")## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_line()`).## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_ribbon()`).
ggplot(data = comp_ewo[comp_ewo$year == 2023,], aes(x = age)) +
geom_point(aes(y = german_girls)) +
geom_line(aes(y = german_girls)) +
geom_ribbon(aes(ymin = german_girls_lb, ymax = german_girls_ub), alpha = .2) +
geom_point(aes(y = german_girls_ewo), color = "red") +
geom_line(aes(y = german_girls_ewo), color = "red") +
theme_minimal() +
coord_cartesian(ylim = c(.5, 1)) +
ggtitle("girls, 2023")## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_line()`).## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_ribbon()`).
ggplot(data = comp_ewo[comp_ewo$year == 2023,], aes(x = age)) +
geom_point(aes(y = german_boys)) +
geom_line(aes(y = german_boys)) +
geom_ribbon(aes(ymin = german_boys_lb, ymax = german_boys_ub), alpha = .2) +
geom_point(aes(y = german_boys_ewo), color = "red") +
geom_line(aes(y = german_boys_ewo), color = "red") +
theme_minimal() +
coord_cartesian(ylim = c(.5, 1)) +
ggtitle("boys, 2023")## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_line()`).## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_ribbon()`).
round(prop.table(table(youth2010$s23aa)),2)##
## 121 126 129 134 137 140 142 146 150 151 152 158 160 163 166 169
## 0.01 0.02 0.01 0.01 0.01 0.01 0.02 0.01 0.01 0.01 0.01 0.01 0.16 0.05 0.14 0.01
## 170 221 245 326 335 348 351 361 368 386 423 425 430 432 434 436
## 0.01 0.01 0.01 0.01 0.01 0.01 0.01 0.01 0.01 0.01 0.05 0.01 0.01 0.05 0.01 0.01
## 437 438 439 444 450 451 461 475 476 477 536 998
## 0.01 0.08 0.01 0.14 0.01 0.01 0.01 0.01 0.01 0.02 0.01 0.01round(prop.table(table(youth2010$s23ba)),2)##
## 0 121 122 125 126 129 130 131 132 134 137 140 142 144 148 150
## 0.01 0.01 0.00 0.01 0.00 0.00 0.00 0.00 0.00 0.00 0.02 0.00 0.01 0.01 0.00 0.00
## 151 152 153 154 157 158 159 160 161 163 165 166 168 169 170 195
## 0.01 0.03 0.01 0.00 0.01 0.00 0.01 0.10 0.00 0.06 0.01 0.05 0.01 0.00 0.01 0.00
## 221 223 225 238 248 252 254 262 269 276 282 285 287 289 326 332
## 0.03 0.01 0.00 0.00 0.00 0.01 0.02 0.00 0.00 0.00 0.00 0.01 0.01 0.00 0.00 0.01
## 348 351 361 367 368 423 425 430 431 432 434 436 437 438 439 444
## 0.00 0.02 0.02 0.00 0.01 0.03 0.01 0.01 0.00 0.14 0.00 0.02 0.00 0.04 0.00 0.07
## 445 450 451 458 461 475 476 477 479 996 998
## 0.01 0.00 0.01 0.00 0.01 0.01 0.00 0.01 0.00 0.00 0.03round(prop.table(table(youth2010$s23ca)),2)##
## 121 125 126 129 130 131 134 140 142 146 151 152 155 158 159 160
## 0.01 0.02 0.00 0.00 0.01 0.00 0.01 0.00 0.01 0.00 0.01 0.07 0.00 0.00 0.01 0.12
## 161 163 164 165 166 169 170 223 227 262 289 326 327 332 361 423
## 0.00 0.04 0.01 0.00 0.11 0.00 0.02 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.04
## 425 430 432 434 436 437 438 439 444 450 451 461 462 470 475 476
## 0.00 0.01 0.17 0.00 0.01 0.00 0.05 0.01 0.08 0.00 0.00 0.00 0.00 0.01 0.00 0.01
## 477 996 998
## 0.01 0.00 0.04# Compare precise migration background
prop.table(table(youth2010$migback[youth2010$migback != "none"]))##
## both father mother self
## 0.17886179 0.33333333 0.09485095 0.39295393prop.table(table(youth2023$migback[youth2023$migback != "none"]))##
## both father mother self
## 0.2500000 0.2277397 0.1438356 0.3784247prop.table(table(youth2023$staat_geb_person)) # self##
## 1 2
## 0.92068849 0.07931151prop.table(table(youth2010$s23ad, useNA = "always"))##
## 1 <NA>
## 0.93031937 0.06968063prop.table(table(youth2023$staat_geb_vater)) # father##
## 1 2
## 0.8334473 0.1665527prop.table(table(youth2010$s23bd, useNA = "always"))##
## 1 <NA>
## 0.8419743 0.1580257prop.table(table(youth2023$staat_geb_mutter)) # mother##
## 1 2
## 0.8511566 0.1488434prop.table(table(youth2010$s23cd, useNA = "always"))##
## 1 <NA>
## 0.886769 0.113231A brief look at countries of origin in 2010
This is to check how many students with a Vietnamese migration background are in our 2010 data, reported in the discussion section.
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union# self born in Germany? if no, which country
table(youth2010$s23aa)##
## 121 126 129 134 137 140 142 146 150 151 152 158 160 163 166 169 170 221 245 326
## 2 3 1 1 1 1 3 1 1 1 2 1 24 8 21 1 2 1 1 1
## 335 348 351 361 368 386 423 425 430 432 434 436 437 438 439 444 450 451 461 475
## 1 1 2 1 1 1 7 1 2 8 1 1 1 12 1 21 1 1 1 1
## 476 477 536 998
## 1 3 1 2# father born in Germany? if no, which country
table(youth2010$s23ba)##
## 0 121 122 125 126 129 130 131 132 134 137 140 142 144 148 150 151 152 153 154
## 4 3 1 3 1 1 1 1 1 1 6 1 3 2 1 1 2 10 4 1
## 157 158 159 160 161 163 165 166 168 169 170 195 221 223 225 238 248 252 254 262
## 2 1 2 31 1 20 4 17 2 1 2 1 9 2 1 1 1 4 7 1
## 269 276 282 285 287 289 326 332 348 351 361 367 368 423 425 430 431 432 434 436
## 1 1 1 2 3 1 1 2 1 6 5 1 3 8 3 2 1 46 1 6
## 437 438 439 444 445 450 451 458 461 475 476 477 479 996 998
## 1 13 1 21 2 1 2 1 2 4 1 3 1 1 11# mother born in Germany? if no, which country
table(youth2010$s23ca)##
## 121 125 126 129 130 131 134 140 142 146 151 152 155 158 159 160 161 163 164 165
## 2 5 1 1 2 1 2 1 3 1 2 16 1 1 2 29 1 10 2 1
## 166 169 170 223 227 262 289 326 327 332 361 423 425 430 432 434 436 437 438 439
## 25 1 4 1 1 1 1 1 1 1 1 10 1 3 40 1 3 1 12 2
## 444 450 451 461 462 470 475 476 477 996 998
## 18 1 1 1 1 2 1 2 2 1 10unique_countries <- unique(c(youth2010$s23aa,
youth2010$s23ba,
youth2010$s23ca))
unique_countries <- unique_countries[!is.na(unique_countries)]
unique_countries <- sort(unique_countries)
key_table <- data.frame(matrix(NA, ncol = 2,
nrow = length(unique_countries)))
names(key_table) <- c("code", "country")
key_table$code <- unique_countries
key_table$n <- NA
for (i in 1:nrow(key_table)) {
key_table$n[i] <- sum(youth2010$s23aa == key_table$code[i], na.rm = TRUE) +
sum(youth2010$s23ba == key_table$code[i], na.rm = TRUE) +
sum(youth2010$s23ca == key_table$code[i], na.rm = TRUE)
}
key_table$country[key_table$n < 5] <- "small"
key_table$code[is.na(key_table$country)]## [1] 121 125 126 137 142 151 152 160 163 165 166 170 221 254 351 361 423 425 430
## [20] 432 436 438 444 475 477 998key_table$country[key_table$code == "121"] <- "Albania"
key_table$country[key_table$code == "125"] <- "Bulgaria"
key_table$country[key_table$code == "126"] <- "Denmark"
key_table$country[key_table$code == "137"] <- "Italy"
key_table$country[key_table$code == "142"] <- "Lithuania"
key_table$country[key_table$code == "151"] <- "Austria"
key_table$country[key_table$code == "152"] <- "Poland"
key_table$country[key_table$code == "160"] <- "Russia"
key_table$country[key_table$code == "163"] <- "Turkey"
key_table$country[key_table$code == "165"] <- "Hungary"
key_table$country[key_table$code == "166"] <- "Ukraine"
key_table$country[key_table$code == "170"] <- "Serbia"
key_table$country[key_table$code == "221"] <- "Algeria"
key_table$country[key_table$code == "254"] <- "Mozambique"
key_table$country[key_table$code == "351"] <- "Cuba"
key_table$country[key_table$code == "361"] <- "Peru"
key_table$country[key_table$code == "423"] <- "Afghanistan"
key_table$country[key_table$code == "425"] <- "Azerbaijan"
key_table$country[key_table$code == "430"] <- "Georgia"
key_table$country[key_table$code == "432"] <- "Vietnam"
key_table$country[key_table$code == "436"] <- "India"
key_table$country[key_table$code == "438"] <- "Iraq"
key_table$country[key_table$code == "444"] <- "Kazakhstan"
key_table$country[key_table$code == "475"] <- "Syria"
key_table$country[key_table$code == "477"] <- "Usbekistan"
key_table$country[key_table$code == "998"] <- "small"
youth2010 <- youth2010 %>%
left_join(key_table, by = c("s23aa" = "code")) %>%
rename(s23aa_country = country) %>%
left_join(key_table, by = c("s23ba" = "code")) %>%
rename(s23ba_country = country) %>%
left_join(key_table, by = c("s23ca" = "code")) %>%
rename(s23ca_country = country)
youth2010$s23aa_country[youth2010$migback == "none"] <- "Germany"
youth2010$s23ba_country[youth2010$migback == "none"] <- "Germany"
youth2010$s23ca_country[youth2010$migback == "none"] <- "Germany"
youth2010 <- youth2010 %>%
mutate(s23aa_country = ifelse(s23aa_country %in% names(which(table(s23aa_country) < 5)),
"small",
s23aa_country))
youth2010 <- youth2010 %>%
mutate(s23ba_country = ifelse(s23ba_country %in% names(which(table(s23ba_country) < 5)),
"small",
s23ba_country))
youth2010 <- youth2010 %>%
mutate(s23ca_country = ifelse(s23ca_country %in% names(which(table(s23ca_country) < 5)),
"small",
s23ca_country))
table(youth2010$s23aa_country)##
## Afghanistan Germany Iraq Kazakhstan Russia small
## 7 1983 12 21 24 44
## Turkey Ukraine Vietnam
## 8 21 8table(youth2010$s23ba_country)##
## Afghanistan Algeria Cuba Germany India Iraq
## 8 9 6 1983 6 13
## Italy Kazakhstan Mozambique Peru Poland Russia
## 6 21 7 5 10 31
## small Turkey Ukraine Vietnam
## 113 20 17 46table(youth2010$s23ca_country)##
## Afghanistan Bulgaria Germany Iraq Kazakhstan Poland
## 10 5 1983 12 18 16
## Russia small Turkey Ukraine Vietnam
## 29 70 10 25 40