ChoiYingDebbie_Wong_Research_Report
2024-04-04
rm(list=ls()); gc() ## used (Mb) gc trigger (Mb) limit (Mb) max used (Mb)
## Ncells 526467 28.2 1169431 62.5 NA 669520 35.8
## Vcells 968248 7.4 8388608 64.0 16384 1851694 14.2##Setting up the environment
# List of packages
packages <- c("tidyverse", "infer", "fst", "modelsummary", "effects", "survey", "MASS", "aod", "interactions", "kableExtra", "flextable", "scales") # add any you need here
# Install packages if they aren't installed already
new_packages <- packages[!(packages %in% installed.packages()[,"Package"])]
if(length(new_packages)) install.packages(new_packages)
# Load the packages
lapply(packages, library, character.only = TRUE)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ 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: carData
##
## lattice theme set by effectsTheme()
## See ?effectsTheme for details.
##
## Loading required package: grid
##
## Loading required package: Matrix
##
##
## Attaching package: 'Matrix'
##
##
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack
##
##
## Loading required package: survival
##
##
## Attaching package: 'survey'
##
##
## The following object is masked from 'package:graphics':
##
## dotchart
##
##
##
## Attaching package: 'MASS'
##
##
## The following object is masked from 'package:dplyr':
##
## select
##
##
##
## Attaching package: 'aod'
##
##
## The following object is masked from 'package:survival':
##
## rats
##
##
##
## Attaching package: 'kableExtra'
##
##
## The following object is masked from 'package:dplyr':
##
## group_rows
##
##
##
## Attaching package: 'flextable'
##
##
## The following objects are masked from 'package:kableExtra':
##
## as_image, footnote
##
##
## The following object is masked from 'package:purrr':
##
## compose
##
##
##
## Attaching package: 'scales'
##
##
## The following object is masked from 'package:purrr':
##
## discard
##
##
## The following object is masked from 'package:readr':
##
## col_factor## [[1]]
## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [13] "grDevices" "utils" "datasets" "methods" "base"
##
## [[2]]
## [1] "infer" "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [7] "readr" "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [13] "graphics" "grDevices" "utils" "datasets" "methods" "base"
##
## [[3]]
## [1] "fst" "infer" "lubridate" "forcats" "stringr" "dplyr"
## [7] "purrr" "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [13] "stats" "graphics" "grDevices" "utils" "datasets" "methods"
## [19] "base"
##
## [[4]]
## [1] "modelsummary" "fst" "infer" "lubridate" "forcats"
## [6] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [11] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [16] "grDevices" "utils" "datasets" "methods" "base"
##
## [[5]]
## [1] "effects" "carData" "modelsummary" "fst" "infer"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[6]]
## [1] "survey" "survival" "Matrix" "grid" "effects"
## [6] "carData" "modelsummary" "fst" "infer" "lubridate"
## [11] "forcats" "stringr" "dplyr" "purrr" "readr"
## [16] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [21] "graphics" "grDevices" "utils" "datasets" "methods"
## [26] "base"
##
## [[7]]
## [1] "MASS" "survey" "survival" "Matrix" "grid"
## [6] "effects" "carData" "modelsummary" "fst" "infer"
## [11] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [16] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [21] "stats" "graphics" "grDevices" "utils" "datasets"
## [26] "methods" "base"
##
## [[8]]
## [1] "aod" "MASS" "survey" "survival" "Matrix"
## [6] "grid" "effects" "carData" "modelsummary" "fst"
## [11] "infer" "lubridate" "forcats" "stringr" "dplyr"
## [16] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [21] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [26] "datasets" "methods" "base"
##
## [[9]]
## [1] "interactions" "aod" "MASS" "survey" "survival"
## [6] "Matrix" "grid" "effects" "carData" "modelsummary"
## [11] "fst" "infer" "lubridate" "forcats" "stringr"
## [16] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [21] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [26] "utils" "datasets" "methods" "base"
##
## [[10]]
## [1] "kableExtra" "interactions" "aod" "MASS" "survey"
## [6] "survival" "Matrix" "grid" "effects" "carData"
## [11] "modelsummary" "fst" "infer" "lubridate" "forcats"
## [16] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [21] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [26] "grDevices" "utils" "datasets" "methods" "base"
##
## [[11]]
## [1] "flextable" "kableExtra" "interactions" "aod" "MASS"
## [6] "survey" "survival" "Matrix" "grid" "effects"
## [11] "carData" "modelsummary" "fst" "infer" "lubridate"
## [16] "forcats" "stringr" "dplyr" "purrr" "readr"
## [21] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [26] "graphics" "grDevices" "utils" "datasets" "methods"
## [31] "base"
##
## [[12]]
## [1] "scales" "flextable" "kableExtra" "interactions" "aod"
## [6] "MASS" "survey" "survival" "Matrix" "grid"
## [11] "effects" "carData" "modelsummary" "fst" "infer"
## [16] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [21] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [26] "stats" "graphics" "grDevices" "utils" "datasets"
## [31] "methods" "base"##Loading the data
spain_data <- read_fst("spain_data.fst")##Examining data set
# Directly summarize the 'edulvlb' variable
summary(spain_data$edulvlb)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.0 129.0 222.0 382.3 520.0 9999.0 7844# Directly summarize the 'polintr' variable
summary(spain_data$polintr)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.00 2.00 3.00 2.87 4.00 9.00# Check for missing values in 'edulvlb' and 'polintr'
sum(is.na(spain_data$edulvlb))## [1] 7844sum(is.na(spain_data$polintr))## [1] 0##Recoding
# Recoding 'edulvlb'
spain_data <- spain_data %>%
mutate(edulvlb_recode = case_when(
edulvlb == "No formal education" ~ 1,
edulvlb == "Primary education" ~ 2,
edulvlb == "Secondary education" ~ 3,
edulvlb == "Tertiary education" ~ 4,
TRUE ~ NA_real_ # Handles cases that do not fit the above categories
))spain_data <- spain_data %>%
filter(!is.na(edulvlb) & !is.na(polintr))summary_table <- spain_data %>%
group_by(edulvlb_recode) %>%
summarise(
Mean_Political_Interest = mean(polintr, na.rm = TRUE),
N = n()
)##visualizing
ggplot(spain_data, aes(x = factor(edulvlb_recode), y = polintr)) +
geom_boxplot() +
labs(x = "Education Level", y = "Political Interest",
title = "Political Interest by Education Level in Spain") +
scale_x_discrete(labels = c("1" = "No formal", "2" = "Primary", "3" = "Secondary", "4" = "Tertiary"))
##Examining data set
# Directly summarize the 'edulvlb' variable
summary(spain_data$edulvlb)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 129.0 222.0 382.3 520.0 9999.0# Directly summarize the 'polintr' variable
summary(spain_data$polintr)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.000 2.000 3.000 2.752 3.000 9.000# Check for missing values in 'edulvlb' and 'polintr'
sum(is.na(spain_data$edulvlb))## [1] 0sum(is.na(spain_data$polintr))## [1] 0##Recoding
# Recoding 'edulvlb'
spain_data <- spain_data %>%
mutate(edulvlb_recode = case_when(
edulvlb == "No formal education" ~ 1,
edulvlb == "Primary education" ~ 2,
edulvlb == "Secondary education" ~ 3,
edulvlb == "Tertiary education" ~ 4,
TRUE ~ NA_real_ # Handles cases that do not fit the above categories
))spain_data <- spain_data %>%
filter(!is.na(edulvlb) & !is.na(polintr))summary_table <- spain_data %>%
group_by(edulvlb_recode) %>%
summarise(
Mean_Political_Interest = mean(polintr, na.rm = TRUE),
N = n()
)##visualizing
# Descriptive statistics for political interest by education level
spain_data %>%
group_by(edulvlb_recode) %>%
summarise(
mean_polintr = mean(polintr, na.rm = TRUE),
sd_polintr = sd(polintr, na.rm = TRUE),
min_polintr = min(polintr, na.rm = TRUE),
max_polintr = max(polintr, na.rm = TRUE),
.groups = 'drop'
)## # A tibble: 1 × 5
## edulvlb_recode mean_polintr sd_polintr min_polintr max_polintr
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 NA 2.75 0.966 1 9# Enhanced Boxplot with Summary Statistics
ggplot(spain_data, aes(x = factor(edulvlb_recode), y = polintr, fill = factor(edulvlb_recode))) +
geom_boxplot() +
stat_summary(fun = "mean", geom = "point", shape = 20, size = 3, color = "red") +
labs(x = "Education Level", y = "Political Interest", title = "Political Interest by Education Level in Spain") +
scale_fill_brewer(palette = "Pastel1") +
theme_minimal()
# Generating a detailed summary of political interest by education level
detailed_summary <- spain_data %>%
group_by(edulvlb_recode) %>%
summarise(
Mean_Political_Interest = mean(polintr, na.rm = TRUE),
Median_Political_Interest = median(polintr, na.rm = TRUE),
Std_Deviation = sd(polintr, na.rm = TRUE),
Count = n(),
.groups = 'drop'
)
print(detailed_summary)## # A tibble: 1 × 5
## edulvlb_recode Mean_Political_Interest Median_Political_Interest Std_Deviation
## <dbl> <dbl> <dbl> <dbl>
## 1 NA 2.75 3 0.966
## # ℹ 1 more variable: Count <int>## Not necessary, but always good to rename when doing operations so you can backtrack to clean dataset
tab_dat <- spain_data
# Create a crosstable and save it into the object mytab
mytab <- table(tab_dat$edulvlb,tab_dat$polintr)
# Calculate row-wise sums of counts in table
rsums <- rowSums(mytab)
# Calculate column-wise sums of counts in table
csums <- colSums(mytab)
# Get the total count of the table (N)
N <- sum(mytab)
# Generate table of expected proportions
ptab <- tcrossprod(rsums/N, csums/N)
cat("Table of Expected Proportions:\n")## Table of Expected Proportions:print(ptab)## [,1] [,2] [,3] [,4] [,5]
## [1,] 9.734807e-03 0.0225314263 0.0323394822 0.0202973285 5.859929e-05
## [2,] 1.839454e-02 0.0425745796 0.0611075322 0.0383531080 1.107271e-04
## [3,] 8.482202e-04 0.0019632246 0.0028178272 0.0017685615 5.105916e-06
## [4,] 2.449976e-02 0.0567052310 0.0813893351 0.0510826382 1.474778e-04
## [5,] 5.247130e-03 0.0121445986 0.0174312103 0.0109404040 3.158543e-05
## [6,] 6.904118e-05 0.0001597973 0.0002293580 0.0001439527 4.155978e-07
## [7,] 5.444390e-03 0.0126011624 0.0180865189 0.0113516974 3.277285e-05
## [8,] 9.152888e-03 0.0211845629 0.0304063216 0.0190840130 5.509639e-05
## [9,] 2.978634e-03 0.0068941142 0.0098951607 0.0062105301 1.793008e-05
## [10,] 6.006583e-03 0.0139023694 0.0199541486 0.0125238835 3.615701e-05
## [11,] 3.777539e-03 0.0087431979 0.0125491608 0.0078762683 2.273914e-05
## [12,] 1.188495e-02 0.0275079724 0.0394823465 0.0247804263 7.154219e-05
## [13,] 1.454796e-02 0.0336715844 0.0483290134 0.0303328870 8.757239e-05
## [14,] 1.203289e-03 0.0027850395 0.0039973828 0.0025088896 7.243276e-06
## [15,] 9.863026e-05 0.0002282819 0.0003276543 0.0002056467 5.937111e-07
## [16,] 5.917816e-05 0.0001369692 0.0001965926 0.0001233880 3.562267e-07
## [17,] 5.917816e-05 0.0001369692 0.0001965926 0.0001233880 3.562267e-07
## [18,] 4.832883e-04 0.0011185814 0.0016055062 0.0010076688 2.909185e-06
## [,6] [,7]
## [1,] 4.394947e-05 2.197473e-05
## [2,] 8.304534e-05 4.152267e-05
## [3,] 3.829437e-06 1.914718e-06
## [4,] 1.106084e-04 5.530419e-05
## [5,] 2.368907e-05 1.184454e-05
## [6,] 3.116983e-07 1.558492e-07
## [7,] 2.457964e-05 1.228982e-05
## [8,] 4.132229e-05 2.066115e-05
## [9,] 1.344756e-05 6.723779e-06
## [10,] 2.711776e-05 1.355888e-05
## [11,] 1.705435e-05 8.527176e-06
## [12,] 5.365664e-05 2.682832e-05
## [13,] 6.567929e-05 3.283965e-05
## [14,] 5.432457e-06 2.716228e-06
## [15,] 4.452833e-07 2.226417e-07
## [16,] 2.671700e-07 1.335850e-07
## [17,] 2.671700e-07 1.335850e-07
## [18,] 2.181888e-06 1.090944e-06# Table of expected frequencies
ftab <- N * ptab
cat("Table of Expected Frequencies:\n")## Table of Expected Frequencies:##Summarizing data
# Load necessary libraries
library(tidyverse)
# Generate descriptive statistics for 'polintr'
spain_data %>%
summarise(
Mean_Political_Interest = mean(polintr, na.rm = TRUE),
SD_Political_Interest = sd(polintr, na.rm = TRUE),
Median_Political_Interest = median(polintr, na.rm = TRUE),
Min_Political_Interest = min(polintr, na.rm = TRUE),
Max_Political_Interest = max(polintr, na.rm = TRUE)
)## Mean_Political_Interest SD_Political_Interest Median_Political_Interest
## 1 2.751637 0.9660815 3
## Min_Political_Interest Max_Political_Interest
## 1 1 9# Generate a frequency table for 'edulvlb_recode'
spain_data %>%
count(edulvlb_recode)## edulvlb_recode n
## 1 NA 11608# Crosstab of education level and political interest categories
spain_data %>%
group_by(edulvlb_recode) %>%
count(polintr)## # A tibble: 7 × 3
## # Groups: edulvlb_recode [1]
## edulvlb_recode polintr n
## <dbl> <dbl> <int>
## 1 NA 1 1329
## 2 NA 2 3076
## 3 NA 3 4415
## 4 NA 4 2771
## 5 NA 7 8
## 6 NA 8 6
## 7 NA 9 3# Comparative summary statistics by education level
spain_data %>%
group_by(edulvlb_recode) %>%
summarise(
Mean_Political_Interest = mean(polintr, na.rm = TRUE),
SD_Political_Interest = sd(polintr, na.rm = TRUE),
.groups = 'drop'
)## # A tibble: 1 × 3
## edulvlb_recode Mean_Political_Interest SD_Political_Interest
## <dbl> <dbl> <dbl>
## 1 NA 2.75 0.966