Launch a new R project and R markdown file. Name it “Lastname_Firstname_Project_202”. Set up your environment with packages you will use.
packages <- c("tidyverse", "modelsummary", "forcats", "RColorBrewer",
"fst", "viridis", "knitr", "rmarkdown", "ggridges", "viridis", "questionr", "flextable", "infer") # add any you need here
new_packages <- packages[!(packages %in% installed.packages()[,"Package"])]
if(length(new_packages)) install.packages(new_packages)
lapply(packages, library, character.only = TRUE)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.3 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── 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: viridisLite
##
##
## Attaching package: 'flextable'
##
##
## The following object is masked from 'package:purrr':
##
## compose## [[1]]
## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [13] "grDevices" "utils" "datasets" "methods" "base"
##
## [[2]]
## [1] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [6] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [11] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [16] "datasets" "methods" "base"
##
## [[3]]
## [1] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [6] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [11] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [16] "datasets" "methods" "base"
##
## [[4]]
## [1] "RColorBrewer" "modelsummary" "lubridate" "forcats" "stringr"
## [6] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [11] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [16] "utils" "datasets" "methods" "base"
##
## [[5]]
## [1] "fst" "RColorBrewer" "modelsummary" "lubridate" "forcats"
## [6] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [11] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [16] "grDevices" "utils" "datasets" "methods" "base"
##
## [[6]]
## [1] "viridis" "viridisLite" "fst" "RColorBrewer" "modelsummary"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[7]]
## [1] "knitr" "viridis" "viridisLite" "fst" "RColorBrewer"
## [6] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [11] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [16] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [21] "datasets" "methods" "base"
##
## [[8]]
## [1] "rmarkdown" "knitr" "viridis" "viridisLite" "fst"
## [6] "RColorBrewer" "modelsummary" "lubridate" "forcats" "stringr"
## [11] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [16] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [21] "utils" "datasets" "methods" "base"
##
## [[9]]
## [1] "ggridges" "rmarkdown" "knitr" "viridis" "viridisLite"
## [6] "fst" "RColorBrewer" "modelsummary" "lubridate" "forcats"
## [11] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [16] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [21] "grDevices" "utils" "datasets" "methods" "base"
##
## [[10]]
## [1] "ggridges" "rmarkdown" "knitr" "viridis" "viridisLite"
## [6] "fst" "RColorBrewer" "modelsummary" "lubridate" "forcats"
## [11] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [16] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [21] "grDevices" "utils" "datasets" "methods" "base"
##
## [[11]]
## [1] "questionr" "ggridges" "rmarkdown" "knitr" "viridis"
## [6] "viridisLite" "fst" "RColorBrewer" "modelsummary" "lubridate"
## [11] "forcats" "stringr" "dplyr" "purrr" "readr"
## [16] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [21] "graphics" "grDevices" "utils" "datasets" "methods"
## [26] "base"
##
## [[12]]
## [1] "flextable" "questionr" "ggridges" "rmarkdown" "knitr"
## [6] "viridis" "viridisLite" "fst" "RColorBrewer" "modelsummary"
## [11] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [16] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [21] "stats" "graphics" "grDevices" "utils" "datasets"
## [26] "methods" "base"
##
## [[13]]
## [1] "infer" "flextable" "questionr" "ggridges" "rmarkdown"
## [6] "knitr" "viridis" "viridisLite" "fst" "RColorBrewer"
## [11] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [16] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [21] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [26] "datasets" "methods" "base"ess <- read_fst("All-ESS-Data.fst")Filter to your country of interest and save the dataset.
German_data <- ess %>%
filter(cntry == "DE")
write_fst(German_data, "~/Desktop/YiLin_Zhou_Project_202/German_data.fst")Clean your environment and load in the filtered dataset.
rm(list=ls()); gc()## used (Mb) gc trigger (Mb) limit (Mb) max used (Mb)
## Ncells 1263724 67.5 2131127 113.9 NA 2131127 113.9
## Vcells 2153637 16.5 1257021492 9590.4 16384 1396873835 10657.4df <- read_fst("~/Desktop/YiLin_Zhou_Project_202/German_data.fst")Produce and save a data summary output (using data summary skim) for potential outcomes of interest on a similar scale (e.g., 0-10, or 1 to 6, or binary). Add a title. You can do so while coding (explore package information for flextable and/or modelsummary) or add it directly in the word file. Title should be something like: Table 1: Descriptive Statistics for outcome variables. You can alter the title as you see fit.
df$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
df$year[df$essround == i] <- replacements[i]
}
German_data <- df
German_data_table_subset <- German_data %>%
mutate(
ipfrule = ifelse(ipfrule %in% c(7, 8, 9), NA, ipfrule),
alcfreq = ifelse(iprspot %in% c(77, 88, 99), NA, iprspot),
trstlgl = ifelse(trstplt %in% c(77, 88, 99), NA, trstplt)
)
summary_table <- datasummary_skim(German_data_table_subset %>% select(ipfrule, alcfreq, trstlgl), output = "flextable")## Warning: The histogram argument is only supported for (a) output types "default",
## "html", "kableExtra", or "gt"; (b) writing to file paths with extensions
## ".html", ".jpg", or ".png"; and (c) Rmarkdown, knitr or Quarto documents
## compiled to PDF (via kableExtra) or HTML (via kableExtra or gt). Use
## `histogram=FALSE` to silence this warning.summary_table
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
|---|---|---|---|---|---|---|---|
ipfrule | 7 | 27 | 3.4 | 1.4 | 1.0 | 3.0 | 6.0 |
alcfreq | 10 | 26 | 3.4 | 1.4 | 1.0 | 3.0 | 9.0 |
trstlgl | 12 | 1 | 3.6 | 2.2 | 0.0 | 4.0 | 10.0 |
German_data_v2 <- German_data_table_subset %>%
rename(
`Trust in the legal system` = ipfrule,
`How often drink alcohol` = alcfreq,
`Important to do what is told and follow rules` = trstlgl
)summary_table_v2 <- datasummary_skim(German_data_v2 %>% select(`Trust in the legal system`,`How often drink alcohol`, `Important to do what is told and follow rules`), output = "flextable", title = "Table 1: Descriptive Statistics for outcome variables")## Warning: The histogram argument is only supported for (a) output types "default",
## "html", "kableExtra", or "gt"; (b) writing to file paths with extensions
## ".html", ".jpg", or ".png"; and (c) Rmarkdown, knitr or Quarto documents
## compiled to PDF (via kableExtra) or HTML (via kableExtra or gt). Use
## `histogram=FALSE` to silence this warning.summary_table_v2
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
|---|---|---|---|---|---|---|---|
Trust in the legal system | 7 | 27 | 3.4 | 1.4 | 1.0 | 3.0 | 6.0 |
How often drink alcohol | 10 | 26 | 3.4 | 1.4 | 1.0 | 3.0 | 9.0 |
Important to do what is told and follow rules | 12 | 1 | 3.6 | 2.2 | 0.0 | 4.0 | 10.0 |
Produce and save a data summary output (using data summary skim) for socio-demographic variables. Add a title. You can do so while coding (explore package information for flextable and/or modelsummary) or add it directly in the word file. Title should be something like: Table 1: Descriptive Statistics for socio-demographic variables. You can alter the title as you see fit.
German_data_table_subset <- German_data %>%
mutate(
lvgptnea = ifelse(lvgptnea %in% c(6, 7, 8, 9), NA, lvgptnea),
marsts = ifelse(marsts %in% c(66, 77, 88, 99), NA, marsts),
emplrel = ifelse(emplrel %in% c(6, 7, 8, 9), NA, emplrel)
)
German_data_v2 <- German_data_table_subset %>%
rename(
`Ever lived with a partner, without being married` = lvgptnea,
`Legal marital status` = marsts,
`Employment relation` = emplrel
)
summary_table_v2 <- datasummary_skim(German_data_v2 %>% select(`Ever lived with a partner, without being married`,`Legal marital status`, `Employment relation`), output = "flextable", title = "Table 1: Descriptive Statistics for socio-demographic variables")## Warning: The histogram argument is only supported for (a) output types "default",
## "html", "kableExtra", or "gt"; (b) writing to file paths with extensions
## ".html", ".jpg", or ".png"; and (c) Rmarkdown, knitr or Quarto documents
## compiled to PDF (via kableExtra) or HTML (via kableExtra or gt). Use
## `histogram=FALSE` to silence this warning.summary_table_v2
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
|---|---|---|---|---|---|---|---|
Ever lived with a partner, without being married | 3 | 41 | 1.6 | 0.5 | 1.0 | 2.0 | 2.0 |
Legal marital status | 7 | 81 | 5.3 | 1.2 | 1.0 | 6.0 | 6.0 |
Employment relation | 4 | 8 | 1.1 | 0.4 | 1.0 | 1.0 | 3.0 |