Paid parental leave and fertility
19 April, 2025
Init
library(kirkegaard)## Loading required package: tidyverse## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.4
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
## Loading required package: magrittr
##
##
## Attaching package: 'magrittr'
##
##
## The following object is masked from 'package:purrr':
##
## set_names
##
##
## The following object is masked from 'package:tidyr':
##
## extract
##
##
## Loading required package: weights
##
## Loading required package: Hmisc
##
##
## Attaching package: 'Hmisc'
##
##
## The following objects are masked from 'package:dplyr':
##
## src, summarize
##
##
## The following objects are masked from 'package:base':
##
## format.pval, units
##
##
## Loading required package: assertthat
##
##
## Attaching package: 'assertthat'
##
##
## The following object is masked from 'package:tibble':
##
## has_name
##
##
## Loading required package: psych
##
##
## Attaching package: 'psych'
##
##
## The following object is masked from 'package:Hmisc':
##
## describe
##
##
## The following objects are masked from 'package:ggplot2':
##
## %+%, alpha
##
##
##
## Attaching package: 'kirkegaard'
##
##
## The following object is masked from 'package:psych':
##
## rescale
##
##
## The following object is masked from 'package:assertthat':
##
## are_equal
##
##
## The following object is masked from 'package:purrr':
##
## is_logical
##
##
## The following object is masked from 'package:base':
##
## +load_packages(
readxl,
patchwork,
GGally
)## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2theme_set(theme_bw())
options(
digits = 3
)
#multithreading
#library(future)
#plan(multisession(workers = 8))Functions
Data
#paid leave data
paid_leave1 = read_csv("data/Length of paid leave (calendar days) [WB Gender Portal]/Length of paid leave (calendar days) .csv") %>% df_legalize_names()## Rows: 217 Columns: 4
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): Economy, Economy Code
## dbl (2): Year, Length of paid maternity leave (calendar days)
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.paid_leave2 = read_csv("data/Length of paid leave (calendar days) [WB Gender Portal] (1)/Length of paid leave (calendar days) .csv") %>% df_legalize_names()## Rows: 217 Columns: 4
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): Economy, Economy Code
## dbl (2): Year, Length of paid paternity leave (calendar days)
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.paid_leave3 = read_csv("data/Length of paid leave (calendar days) [WB Gender Portal] (2)/Length of paid leave (calendar days) .csv") %>% df_legalize_names()## Rows: 217 Columns: 4
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): Economy, Economy Code
## dbl (2): Year, Length of paid shared parental leave (calendar days)
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.#fert
fert = read_excel("data/WPP2024_GEN_F01_DEMOGRAPHIC_INDICATORS_COMPACT.xlsx", skip = 16, guess_max = 10000) %>%
filter(!is.na(`ISO3 Alpha-code`)) %>%
df_legalize_names() %>%
select(ISO3_Alpha_code, Year, Total_Fertility_Rate_live_births_per_woman) %>%
rename(
ISO = ISO3_Alpha_code,
TFR = Total_Fertility_Rate_live_births_per_woman
) %>% mutate(
TFR = as.numeric(TFR)
)
#median income
median_inc = read_csv("data/median-income-by-country-2023.csv")## Rows: 162 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): country
## dbl (4): medianIncome, meanIncome, gdpPerCapitaPPP, pop2023
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.#replace 0's with NA
median_inc$gdpPerCapitaPPP %<>% mapvalues(0, NA)
median_inc$meanIncome %<>% mapvalues(0, NA)## The following `from` values were not present in `x`: 0median_inc$medianIncome %<>% mapvalues(0, NA)
#gdp per capita
gdp = read_csv("data/gdp-per-capita-worldbank/gdp-per-capita-worldbank.csv") %>% df_legalize_names() %>% filter(Year == 2019)## Rows: 7063 Columns: 4
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): Entity, Code
## dbl (2): Year, GDP per capita, PPP (constant 2021 international $)
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.#join
d = full_join(
paid_leave1 %>% rename(ISO = Economy_Code, maternal_leave = Length_of_paid_maternity_leave_calendar_days) %>% select(ISO, maternal_leave),
paid_leave2 %>% rename(ISO = Economy_Code, paternal_leave = Length_of_paid_paternity_leave_calendar_days) %>% select(ISO, paternal_leave)
) %>% full_join(
paid_leave3 %>% rename(ISO = Economy_Code, shared_leave = Length_of_paid_shared_parental_leave_calendar_days) %>% select(ISO, shared_leave)
) %>% full_join(
fert %>% filter(Year == 2023) %>% select(ISO, TFR)
) %>% full_join(
median_inc %>% mutate(ISO = pu_translate(country)) %>% select(-country)
) %>% full_join(
gdp %>% rename(ISO = Code, GDPpc = GDP_per_capita_PPP_constant_2021_international) %>% select(ISO, GDPpc) %>% filter(!is.na(ISO))
)## Joining with `by = join_by(ISO)`
## Joining with `by = join_by(ISO)`
## Joining with `by = join_by(ISO)`
## Joining with `by = join_by(ISO)`
## Joining with `by = join_by(ISO)`#data check
assert_that(!anyDuplicated(d$ISO))## [1] TRUEAnalysis
#correlations
d %>%
select(TFR, maternal_leave, paternal_leave, shared_leave) %>%
ggpairs()## Warning: Removed 3 rows containing non-finite outside the scale range
## (`stat_density()`).## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 51 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 51 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 51 rows containing missing values## Warning: Removed 51 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 51 rows containing non-finite outside the scale range
## (`stat_density()`).## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 51 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 51 rows containing missing values## Warning: Removed 51 rows containing missing values or values outside the scale range
## (`geom_point()`).
## Removed 51 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 51 rows containing non-finite outside the scale range
## (`stat_density()`).## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 51 rows containing missing values## Warning: Removed 51 rows containing missing values or values outside the scale range
## (`geom_point()`).
## Removed 51 rows containing missing values or values outside the scale range
## (`geom_point()`).
## Removed 51 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 51 rows containing non-finite outside the scale range
## (`stat_density()`).
GG_save("figs/ggpairs.png")## Warning: Removed 3 rows containing non-finite outside the scale range
## (`stat_density()`).## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 51 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 51 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 51 rows containing missing values## Warning: Removed 51 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 51 rows containing non-finite outside the scale range
## (`stat_density()`).## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 51 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 51 rows containing missing values## Warning: Removed 51 rows containing missing values or values outside the scale range
## (`geom_point()`).
## Removed 51 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 51 rows containing non-finite outside the scale range
## (`stat_density()`).## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 51 rows containing missing values## Warning: Removed 51 rows containing missing values or values outside the scale range
## (`geom_point()`).
## Removed 51 rows containing missing values or values outside the scale range
## (`geom_point()`).
## Removed 51 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 51 rows containing non-finite outside the scale range
## (`stat_density()`).#regression models
d_std = d %>% df_standardize()## Skipped ISO because it is a character (string)list(
lm(TFR ~ maternal_leave + paternal_leave, data = d_std),
lm(TFR ~ maternal_leave + paternal_leave + medianIncome, data = d_std),
lm(TFR ~ maternal_leave + paternal_leave + GDPpc, data = d_std)
) %>%
summarize_models(asterisks_only = F) %>% flextable::flextable()Predictor/Model | 1 | 2 | 3 |
|---|---|---|---|
(Intercept) | 0.10 (0.075, 0.181) | 0.17 (0.066, 0.011) | 0.04 (0.062, 0.503) |
maternal_leave | -0.13 (0.077, 0.099) | -0.21 (0.068, 0.002**) | -0.16 (0.065, 0.018) |
paternal_leave | -0.18 (0.077, 0.02) | -0.02 (0.066, 0.767) | -0.02 (0.065, 0.702) |
medianIncome | -0.63 (0.069, <0.001***) | ||
GDPpc | -0.66 (0.068, <0.001***) | ||
R2 adj. | 0.045 | 0.385 | 0.369 |
N | 189 | 157 | 184 |
Meta
#versions
write_sessioninfo()## R version 4.5.0 (2025-04-11)
## Platform: x86_64-pc-linux-gnu
## Running under: Linux Mint 21.1
##
## Matrix products: default
## BLAS: /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.10.0
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.10.0 LAPACK version 3.10.0
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
## [5] LC_MONETARY=en_DK.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_DK.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_DK.UTF-8 LC_IDENTIFICATION=C
##
## time zone: Europe/Brussels
## tzcode source: system (glibc)
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] GGally_2.2.1 patchwork_1.3.0 readxl_1.4.5
## [4] kirkegaard_2025-03-12 psych_2.5.3 assertthat_0.2.1
## [7] weights_1.0.4 Hmisc_5.2-3 magrittr_2.0.3
## [10] lubridate_1.9.4 forcats_1.0.0 stringr_1.5.1
## [13] dplyr_1.1.4 purrr_1.0.4 readr_2.1.5
## [16] tidyr_1.3.1 tibble_3.2.1 ggplot2_3.5.2
## [19] tidyverse_2.0.0
##
## loaded via a namespace (and not attached):
## [1] Rdpack_2.6.4 mnormt_2.1.1 gridExtra_2.3
## [4] rlang_1.1.6 compiler_4.5.0 gdata_3.0.1
## [7] systemfonts_1.2.2 vctrs_0.6.5 pkgconfig_2.0.3
## [10] shape_1.4.6.1 crayon_1.5.3 fastmap_1.2.0
## [13] backports_1.5.0 labeling_0.4.3 rmarkdown_2.29
## [16] tzdb_0.5.0 nloptr_2.2.1 ragg_1.4.0
## [19] bit_4.6.0 xfun_0.52 glmnet_4.1-8
## [22] jomo_2.7-6 cachem_1.1.0 jsonlite_2.0.0
## [25] uuid_1.2-1 pan_1.9 broom_1.0.8
## [28] parallel_4.5.0 cluster_2.1.8.1 R6_2.6.1
## [31] bslib_0.9.0 stringi_1.8.7 RColorBrewer_1.1-3
## [34] boot_1.3-31 rpart_4.1.24 jquerylib_0.1.4
## [37] cellranger_1.1.0 Rcpp_1.0.14 iterators_1.0.14
## [40] knitr_1.50 base64enc_0.1-3 Matrix_1.7-3
## [43] splines_4.5.0 nnet_7.3-20 timechange_0.3.0
## [46] tidyselect_1.2.1 rstudioapi_0.17.1 yaml_2.3.10
## [49] codetools_0.2-19 lattice_0.22-5 plyr_1.8.9
## [52] withr_3.0.2 askpass_1.2.1 flextable_0.9.7
## [55] evaluate_1.0.3 foreign_0.8-90 survival_3.8-3
## [58] ggstats_0.9.0 zip_2.3.2 xml2_1.3.8
## [61] pillar_1.10.2 mice_3.17.0 checkmate_2.3.2
## [64] foreach_1.5.2 reformulas_0.4.0 generics_0.1.3
## [67] vroom_1.6.5 hms_1.1.3 munsell_0.5.1
## [70] scales_1.3.0 minqa_1.2.8 gtools_3.9.5
## [73] glue_1.8.0 gdtools_0.4.2 tools_4.5.0
## [76] data.table_1.17.0 lme4_1.1-37 grid_4.5.0
## [79] rbibutils_2.3 colorspace_2.1-1 nlme_3.1-168
## [82] htmlTable_2.4.3 Formula_1.2-5 cli_3.6.4
## [85] textshaping_1.0.0 officer_0.6.8 fontBitstreamVera_0.1.1
## [88] gtable_0.3.6 fontquiver_0.2.1 sass_0.4.10
## [91] digest_0.6.37 htmlwidgets_1.6.4 farver_2.1.2
## [94] htmltools_0.5.8.1 lifecycle_1.0.4 mitml_0.4-5
## [97] openssl_2.3.2 fontLiberation_0.1.0 bit64_4.6.0-1
## [100] MASS_7.3-65#write data to file for reuse
d %>% write_rds("data/data_for_reuse.rds")
#OSF
if (F) {
library(osfr)
#login
osf_auth(readr::read_lines("~/.config/osf_token"))
#the project we will use
osf_proj = osf_retrieve_node("https://osf.io/XXX/")
#upload all files in project
#overwrite existing (versioning)
osf_upload(
osf_proj,
path = c("data", "figures", "papers", "notebook.Rmd", "notebook.html", "sessions_info.txt"),
conflicts = "overwrite"
)
}