Amin_Mustafa_Homework_4
2024-03-21
# List of packages
packages <- c("tidyverse", "infer", "fst", "modelsummary", "effects", "survey", "interactions") # 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)## Warning: package 'ggplot2' was built under R version 4.3.3## ── 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 3.5.0 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ 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## Warning: package 'infer' was built under R version 4.3.3## Warning: package 'modelsummary' was built under R version 4.3.3## Version 2.0.0 of `modelsummary`, to be released soon, will introduce a
## breaking change: The default table-drawing package will be `tinytable`
## instead of `kableExtra`. All currently supported table-drawing packages
## will continue to be supported for the foreseeable future, including
## `kableExtra`, `gt`, `huxtable`, `flextable, and `DT`.
##
## You can always call the `config_modelsummary()` function to change the
## default table-drawing package in persistent fashion. To try `tinytable`
## now:
##
## config_modelsummary(factory_default = 'tinytable')
##
## To set the default back to `kableExtra`:
##
## config_modelsummary(factory_default = 'kableExtra')## Warning: package 'effects' was built under R version 4.3.3## Loading required package: carData## Warning: package 'carData' was built under R version 4.3.3## 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## Warning: package 'interactions' was built under R version 4.3.3## [[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] "interactions" "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"hungary_data <- read.fst("hungary_data.fst")# Populist scale (Norris/Inglehart use low levels of trust in parliaments, politicians and parties as an indicator of populism)
# Note: Schafer does it 2 ways, we will focus now on the most straightforward
# Setting values greater than 10 to NA
hungary_data$trstplt <- ifelse(hungary_data$trstplt > 10, NA, hungary_data$trstplt)
hungary_data$trstprl <- ifelse(hungary_data$trstprl > 10, NA, hungary_data$trstprl)
hungary_data$trstprt <- ifelse(hungary_data$trstprt > 10, NA, hungary_data$trstprt)
# Creating and rescaling the trust variable
hungary_data$trust <- scales::rescale(hungary_data$trstplt + hungary_data$trstprl + hungary_data$trstprt, na.rm = TRUE, to = c(0, 100))
# Here's how you would "flip it" because populist is conceived by N + I as 'anti-trust'
# As Schafer explains there are some issues with that conceptualization, but N + I is also widely applied
hungary_data$populist <- scales::rescale(hungary_data$trust, na.rm = TRUE, to=c(100,0))ggplot(hungary_data, aes(x = populist)) +
geom_histogram(bins = 30, fill = "blue", color = "black") +
theme_minimal() +
labs(title = "Distribution of Populist Scale for Hungary",
x = "Populist Scale",
y = "Count")## Warning: Removed 2359 rows containing non-finite outside the scale range
## (`stat_bin()`).
spain_data <- read.fst("spain_data.fst")
# Populist scale (Norris/Inglehart use low levels of trust in parliaments, politicians and parties as an indicator of populism)
# Note: Schafer does it 2 ways, we will focus now on the most straightforward
# Setting values greater than 10 to NA
spain_data$trstplt <- ifelse(spain_data$trstplt > 10, NA, spain_data$trstplt)
spain_data$trstprl <- ifelse(spain_data$trstprl > 10, NA, spain_data$trstprl)
spain_data$trstprt <- ifelse(spain_data$trstprt > 10, NA, spain_data$trstprt)
# Creating and rescaling the trust variable
spain_data$trust <- scales::rescale(spain_data$trstplt + spain_data$trstprl + spain_data$trstprt, na.rm = TRUE, to = c(0, 100))
# Here's how you would "flip it" because populist is conceived by N + I as 'anti-trust'
# As Schafer explains there are some issues with that conceptualization, but N + I is also widely applied
spain_data$populist <- scales::rescale(spain_data$trust, na.rm = TRUE, to=c(100,0))
ggplot(spain_data, aes(x = populist)) +
geom_histogram(bins = 30, fill = "blue", color = "black") +
theme_minimal() +
labs(title = "Distribution of Populist Scale for Spain",
x = "Populist Scale",
y = "Count")## Warning: Removed 2775 rows containing non-finite outside the scale range
## (`stat_bin()`).
Task 1
Graph the histogram distribution using the populist scale (as we did in the tutorial) for the country of Sweden. What do you note?
sweden_data <- read.fst("sweden_data.fst")sweden_data$trstplt <- ifelse(sweden_data$trstplt > 10, NA, sweden_data$trstplt)
sweden_data$trstprl <- ifelse(sweden_data$trstprl > 10, NA, sweden_data$trstprl)
sweden_data$trstprt <- ifelse(sweden_data$trstprt > 10, NA, sweden_data$trstprt)sweden_data$trust <- scales::rescale(sweden_data$trstplt + sweden_data$trstprl + sweden_data$trstprt, na.rm = TRUE, to = c(0, 100))
sweden_data$populist <- scales::rescale(sweden_data$trust, na.rm = TRUE, to=c(100,0))
ggplot(sweden_data, aes(x = populist)) +
geom_histogram(bins = 30, fill = "blue", color = "black") +
theme_minimal() +
labs(title = "Distribution of Populist Scale for Sweden",
x = "Populist Scale",
y = "Count")## Warning: Removed 2503 rows containing non-finite outside the scale range
## (`stat_bin()`).
What is noteworthy from my observation is the outlier in the middle, this represents an irregular level of populist sentiment.
Task 2
Run a linear regression with populist attitudes as the outcome, educational attainment (recoded as a binary “BA or more” and “No BA”), and using the Swedish data. Print the intercept and coefficients only and interpret. Then do a tidy model table displaying the p-value (with digits = 3) and interpret.
sweden_data <- read.fst("sweden_data.fst")# Populist scale (Norris/Inglehart use low levels of trust in parliaments, politicians and parties as an indicator of populism)
# Note: Schafer does it 2 ways, we will focus now on the most straightforward
# Setting values greater than 10 to NA
sweden_data$trstplt <- ifelse(sweden_data$trstplt > 10, NA, sweden_data$trstplt)
sweden_data$trstprl <- ifelse(sweden_data$trstprl > 10, NA, sweden_data$trstprl)
sweden_data$trstprt <- ifelse(sweden_data$trstprt > 10, NA, sweden_data$trstprt)
# Creating and rescaling the trust variable
sweden_data$trust <- scales::rescale(sweden_data$trstplt + sweden_data$trstprl + sweden_data$trstprt, na.rm = TRUE, to = c(0, 100))
# Here's how you would "flip it" because populist is conceived by N + I as 'anti-trust'
# As Schafer explains there are some issues with that conceptualization, but N + I is also widely applied
sweden_data$populist <- scales::rescale(sweden_data$trust, na.rm = TRUE, to=c(100,0))sweden_data <- sweden_data %>%
mutate(
# Recoding education
educ.ba = case_when(
essround < 5 & edulvla == 5 ~ "BA or more",
essround >= 5 & edulvlb > 600 ~ "BA or more",
TRUE ~ "No BA"
),
# Handle NAs for education levels
edulvla = ifelse(edulvla %in% c(77, 88, 99), NA_integer_, edulvla),
edulvlb = ifelse(edulvlb %in% c(5555, 7777, 8888), NA_integer_, edulvlb),
# Explicitly making 'No BA' the reference category
educ.ba = factor(educ.ba, levels = c("No BA", "BA or more")),
)sweden_pop_model <- lm(populist ~ educ.ba, data = sweden_data)coefficients_sweden <- coef(sweden_pop_model)
print(coefficients_sweden)## (Intercept) educ.baBA or more
## 51.358680 -7.868121Interpretation of variab;es: On average, individuals with a BA or more education have a lower mean (average) value of populist attitudes by 7.96 points in comparison with individuals with no BA education.
Task 3
Now using the Italian dataset and the authoritarian values scale (as we did in the tutorial), graph the average by survey year. Interpret.
italy_data <- read.fst("italy_data.fst")df <- read.fst("italy_data.fst")df <- df %>%
mutate(behave = ipbhprp,
secure = impsafe,
safety = ipstrgv,
tradition = imptrad,
rules = ipfrule) %>%
mutate(across(c("behave", "secure", "safety", "tradition", "rules"),
~ na_if(.x, 7) %>% na_if(8) %>% na_if(9))) %>%
# Apply the reverse coding
mutate(across(c("behave", "secure", "safety", "tradition", "rules"), ~ 7 - .x ))
# Now you can calculate 'schwartzauth' after the NA recoding
df$auth <- scales::rescale(df$behave +
df$secure +
df$safety +
df$tradition +
df$rules, to=c(0,100), na.rm=TRUE)
df <- df %>% filter(!is.na(auth))
table(df$secure)##
## 1 2 3 4 5 6
## 54 139 626 1856 2876 2881table(df$auth)##
## 0 12 16 20 24 28 32 36 40 44 48 52 56 60 64 68 72 76 80 84
## 7 4 4 9 13 20 27 57 113 155 163 323 367 596 647 789 823 897 992 733
## 88 92 96 100
## 632 465 299 297ggplot(df, aes(x = auth)) +
geom_histogram(bins = 30, fill = "blue", color = "black") +
theme_minimal() +
labs(title = "Distribution of Authoritarian Scale for Italy",
x = "Authoritarian Scale",
y = "Count")
df$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
df$year[df$essround == i] <- replacements[i]
}
auth_avg <- df %>%
group_by(year) %>%
summarize(auth_avg = mean(auth, na.rm = TRUE))
plot_auth <- ggplot(auth_avg, aes(x = year, y = auth_avg)) +
geom_point(aes(color = auth_avg), alpha = 1.0) +
geom_line(aes(group = 1), color = "blue", linetype = "dashed") +
labs(title = "Authoritarian Scale Average by Year (Italy)",
x = "Survey Year",
y = "Authoritarian Scale Average") +
theme_minimal() +
theme(legend.position = "none") +
scale_y_continuous(limits = c(0, 100))
print(plot_auth)
Interpretation: Authoritarian average scale remained stable around the 75 mark, decreasing steadily till 2016 and seeing a slight resurgence towards 2020.
Task 4
Now run a linear regression model, using the modelsummary package, with authoritarian values as the outcome, and generations as the predictor/potential explanatory variable, and using the Italian data again. Rename the coefficients using the coef_rename function. Interpret the coefficients, whether they are statistically significant, and the adjusted R-squared.
df <- read.fst("italy_data.fst")
## Creates an authoritarian values scale based on human modules items (can also do libertarian value scale)
df <- df %>%
mutate(behave = ipbhprp,
secure = impsafe,
safety = ipstrgv,
tradition = imptrad,
rules = ipfrule) %>%
mutate(across(c("behave", "secure", "safety", "tradition", "rules"),
~ na_if(.x, 7) %>% na_if(8) %>% na_if(9))) %>%
# Apply the reverse coding
mutate(across(c("behave", "secure", "safety", "tradition", "rules"), ~ 7 - .x ))
# Now you can calculate 'schwartzauth' after the NA recoding
df$auth <- scales::rescale(df$behave +
df$secure +
df$safety +
df$tradition +
df$rules, to=c(0,100), na.rm=TRUE)
df <- df %>% filter(!is.na(auth))
table(df$secure)##
## 1 2 3 4 5 6
## 54 139 626 1856 2876 2881model_data <- df %>%
mutate(
# Recoding gender
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
gndr == 9 ~ NA_character_,
TRUE ~ as.character(gndr)
),
# Recoding education
educ.ba = case_when(
essround < 5 & edulvla == 5 ~ "BA or more",
essround >= 5 & edulvlb > 600 ~ "BA or more",
TRUE ~ "No BA"
),
# Handle NAs for education levels
edulvla = ifelse(edulvla %in% c(77, 88, 99), NA_integer_, edulvla),
edulvlb = ifelse(edulvlb %in% c(5555, 7777, 8888), NA_integer_, edulvlb),
# Explicitly making 'No BA' the reference category
educ.ba = factor(educ.ba, levels = c("No BA", "BA or more")),
# Recoding age, setting 999 to NA
age = ifelse(agea == 999, NA, agea),
# Recoding cohort variable, setting years before 1930 and after 2000 to NA
cohort = ifelse(yrbrn < 1930 | yrbrn > 2000, NA, yrbrn),
# Recoding generational cohorts based on year of birth
gen = case_when(
yrbrn %in% 1900:1945 ~ "1",
yrbrn %in% 1946:1964 ~ "2",
yrbrn %in% 1965:1979 ~ "3",
yrbrn %in% 1980:1996 ~ "4",
TRUE ~ as.character(cohort) # Keeping other values as character if they do not fit the ranges
),
# Converting cohort to a factor with labels
gen = factor(gen,
levels = c("1", "2", "3", "4"),
labels = c("Interwar", "Baby Boomers", "Gen X", "Millennials"))
)
table(model_data$gen)##
## Interwar Baby Boomers Gen X Millennials
## 1026 2580 2214 1811model1 <- lm(auth ~ gen, data = model_data)
model2 <- lm(auth ~ gndr, data = model_data)
model3 <- lm(auth ~ educ.ba, data = model_data)# Populist scale (Norris/Inglehart use low levels of trust in parliaments, politicians and parties as an indicator of populism)
# Note: Schafer does it 2 ways, we will focus now on the most straightforward
# Setting values greater than 10 to NA
italy_data$trstplt <- ifelse(italy_data$trstplt > 10, NA, sweden_data$trstplt)
italy_data$trstprl <- ifelse(italy_data$trstprl > 10, NA, sweden_data$trstprl)
italy_data$trstprt <- ifelse(italy_data$trstprt > 10, NA, sweden_data$trstprt)
# Creating and rescaling the trust variable
italy_data$trust <- scales::rescale(italy_data$trstplt + italy_data$trstprl + italy_data$trstprt, na.rm = TRUE, to = c(0, 100))
# Here's how you would "flip it" because populist is conceived by N + I as 'anti-trust'
# As Schafer explains there are some issues with that conceptualization, but N + I is also widely applied
italy_data$populist <- scales::rescale(italy_data$trust, na.rm = TRUE, to=c(100,0))Task 5
Now visualize, using the modelplot() function from the modelsummary package, coefficient estimates and 95% confidence intervals for the following three models:
Model 1 = populist attitudes scale as the outcome; left/right as the single predictor (omitting moderates as we did in the tutorial), and using data for Greece.
Model 2 = populist attitudes scale as the outcome; gender as the single predictor, and using data for Greece.
Model 3 = populist attitudes scale as the outcome; generations as the single predictor (using the four generational category recode we did in the tutorial), and using data for Greece. Interpret.
greece_data <- read.fst("greece_data.fst")model1 <- lm(populist ~ lrvrtl, data = greece_data)