Dean_Bethel_Homework_4
2024-03-19
# 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)## ── 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 3.4.4 ✔ 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## [[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"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$trust, na.rm = TRUE, to=c(100,0))ggplot(sweden_data, aes(x = populist)) +
geom_histogram(bins = 30, fill = "pink", color = "black") +
theme_minimal() +
labs(title = "Distribution of Populist Scale for Sweden",
x = "Populist Scale",
y = "Count")## Warning: Removed 2503 rows containing non-finite values (`stat_bin()`).
The produced histogram above reveals a right skewed distribution. I am also able to note that the majority of people in Sweden report higher levels of trust in populist sect revealed through the low levels of populism according to the scale.
Task 2
Run a linear regression with populist attitudes as the outcome, educational attainment (recoded as a binary “BA or more” and “No BA”), and using the Swedish data. Print the intercept and coefficients only and interpret. Then do a tidy model table displaying the p-value (with digits = 3) and interpret.
sweden_data$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))sweden_data <- sweden_data %>%
mutate(
educ.ba = case_when(
essround < 5 & edulvla == 5 ~ "BA or more",
essround >= 5 & edulvlb > 600 ~ "BA or more",
TRUE ~ "No BA"
)
) %>%
mutate(
edulvla = ifelse(edulvla %in% c(77, 88), NA_integer_, edulvla),
edulvlb = ifelse(edulvlb %in% c(5555, 7777, 8888), NA_integer_, edulvlb),
educ.ba = as.character(educ.ba)
)table(sweden_data$educ.ba)##
## BA or more No BA
## 4739 13477sweden_pop_model <- lm(populist ~ educ.ba, data = sweden_data)
coefficients_sweden <- coef(sweden_pop_model)
print(coefficients_sweden)## (Intercept) educ.baNo BA
## 43.490559 7.868121The intercept 43.4 represents the score for the BA group according to the populist scale.
The coefficient 7.95 appears positive to resemble that those in Sweden with no BA score 7.95 points higher than those with them according to the populist scale.
Task 3
Now using the Italian dataset and the authoritarian values scale (as we did in the tutorial), graph the average by survey year. Interpret.
df <- read.fst("italy_data.fst")
df <- df %>%
mutate(behave = ipbhprp,
secure = impsafe,
safety = ipstrgv,
tradition = imptrad,
rules = ipfrule) %>%
mutate(across(c("behave", "secure", "safety", "tradition", "rules"),
~ na_if(.x, 7) %>% na_if(8) %>% na_if(9))) %>%
mutate(across(c("behave", "secure", "safety", "tradition", "rules"), ~ 7 - .x ))
df$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 2881ggplot(df, aes(x = auth)) +
geom_histogram(bins = 30, fill = "purple", 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$essround == i] <- replacements[i]
}
auth_avg <- df %>%
group_by(year) %>%
summarize(auth_avg = mean(auth, na.rm = TRUE))
plot_auth <- ggplot(auth_avg, aes(x = year, y = auth_avg)) +
geom_point(aes(color = auth_avg), alpha = 1.0) +
geom_line(aes(group = 1), color = "purple", linetype = "dashed") +
labs(title = "Authoritarian Scale Average by Year (Italy)",
x = "Survey Year",
y = "Authoritarian Scale Average") +
theme_minimal() +
theme(legend.position = "none") +
scale_y_continuous(limits = c(0, 100))
print(plot_auth)
The graph reveals a stable flow of authoritarian scale average in relation to the survey year from 2012 till 2020. The only noticeable change can perhaps be recorded in the shift from 2014 to 2016, although this is very slight.
Task 4
Now run a linear regression model, using the modelsummary package, with authoritarian values as the outcome, and generations as the predictor/potential explanatory variable, and using the Italian data again. Rename the coefficients using the coef_rename function. Interpret the coefficients, whether they are statistically significant, and the adjusted R-squared.
model_data <- df %>%
mutate(
age = ifelse(agea == 999, NA, agea),
cohort = ifelse(yrbrn < 1930 | yrbrn > 2000, NA, yrbrn),
gen = case_when(
yrbrn %in% 1900:1945 ~ "1",
yrbrn %in% 1946:1964 ~ "2",
yrbrn %in% 1965:1979 ~ "3",
yrbrn %in% 1980:1996 ~ "4",
TRUE ~ as.character(cohort)
),
gen = factor(gen,
levels = c("1", "2", "3", "4"),
labels = c("Interwar", "Baby Boomers", "Gen X", "Millennials"))
)
table(model_data$gen)##
## Interwar Baby Boomers Gen X Millennials
## 1026 2580 2214 1811model1 <- lm(auth ~ gen, data = model_data) # y ~ mmodelsummary(
list(model1),
fmt = 1,
estimate = c( "{estimate} ({std.error}){stars}"),
statistic = NULL,
coef_omit = "Intercept")| (1) | |
|---|---|
| genBaby Boomers | −1.1 (0.6)* |
| genGen X | −2.1 (0.6)*** |
| genMillennials | −3.6 (0.6)*** |
| Num.Obs. | 7631 |
| R2 | 0.006 |
| R2 Adj. | 0.006 |
| AIC | 62934.0 |
| BIC | 62968.7 |
| Log.Lik. | −31462.009 |
| RMSE | 14.94 |
As the coefficient appears negative, it can be said that there is a lower level of authoritarian in relation to Baby Boomers in comparison with the Intewar generation. Along with this noticeable relation, there are others here but it can be concluded that generation alone does not affect the average level of authoritarianism.
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")greece_data$trstplt <- ifelse(greece_data$trstplt > 10, NA, greece_data$trstplt)
greece_data$trstprl <- ifelse(greece_data$trstprl > 10, NA, greece_data$trstprl)
greece_data$trstprt <- ifelse(greece_data$trstprt > 10, NA, greece_data$trstprt)
greece_data$trust <- scales::rescale(greece_data$trstplt + greece_data$trstprl + greece_data$trstprt, na.rm = TRUE, to = c(0, 100))
greece_data$populist <- scales::rescale(greece_data$trust, na.rm = TRUE, to=c(100,0))model_data <- greece_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
gndr == 9 ~ NA_character_,
TRUE ~ as.character(gndr)
),
lrscale = case_when(
lrscale %in% 0:4 ~ "Left",
lrscale %in% 6:10 ~ "Right",
lrscale %in% c(77, 88, 99) ~ NA_character_,
TRUE ~ NA_character_
),
cohort = ifelse(yrbrn < 1930 | yrbrn > 2000, NA, yrbrn),
gen = case_when(
yrbrn %in% 1900:1945 ~ "1",
yrbrn %in% 1946:1964 ~ "2",
yrbrn %in% 1965:1979 ~ "3",
yrbrn %in% 1980:1996 ~ "4",
TRUE ~ as.character(cohort)
),
gen = factor(gen,
levels = c("1", "2", "3", "4"),
labels = c("Interwar", "Baby Boomers", "Gen X", "Millennials"))
)
table(model_data$gen)##
## Interwar Baby Boomers Gen X Millennials
## 2978 3484 3498 2330model1 <- lm(populist ~ lrscale, data = model_data)
model2 <- lm(populist ~ gndr, data = model_data)
model3 <- lm(populist ~ gen, data = model_data)models <- list(
"Model 1" = lm(populist ~ lrscale, data = model_data),
"Model 2" = lm(populist ~ gndr, data = model_data),
"Model 3" = lm(populist ~ gen, data = model_data))
modelsummary(models, fmt = 1,
estimate = c("{estimate} ({std.error}){stars}",
"{estimate} ({std.error}){stars}",
"{estimate} ({std.error}){stars}"),
statistic = NULL,
coef_rename = c("lrscale" = "Right", "gndrMale" = "Male", "genBaby Boomers" = "Baby Boomers", "genGen X" = "Gen X", "genMillennials" = "Millennials"),
title = 'Table 3. Regression models for populist attitudes')| Model 1 | Model 2 | Model 3 | |
|---|---|---|---|
| (Intercept) | 72.0 (0.5)*** | 70.0 (0.3)*** | 65.8 (0.5)*** |
| lrscaleRight | −8.8 (0.6)*** | ||
| Male | −1.0 (0.5)* | ||
| Baby Boomers | 3.5 (0.7)*** | ||
| Gen X | 5.6 (0.7)*** | ||
| Millennials | 5.8 (0.7)*** | ||
| Num.Obs. | 4936 | 9823 | 9562 |
| R2 | 0.037 | 0.000 | 0.009 |
| R2 Adj. | 0.036 | 0.000 | 0.009 |
| AIC | 44723.8 | 88873.2 | 86473.9 |
| BIC | 44743.3 | 88894.8 | 86509.7 |
| Log.Lik. | −22358.894 | −44433.590 | −43231.944 |
| RMSE | 22.44 | 22.30 | 22.25 |
modelplot(models, coef_omit = 'Interc')