SOC222 HW4
Savannah Williams
2024-03-12
Loading in Packages
# List of packages
packages <- c("tidyverse", "infer", "broom","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 2.1.4
## ✔ 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## [[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] "broom" "infer" "lubridate" "forcats" "stringr" "dplyr"
## [7] "purrr" "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [13] "stats" "graphics" "grDevices" "utils" "datasets" "methods"
## [19] "base"
##
## [[4]]
## [1] "fst" "broom" "infer" "lubridate" "forcats" "stringr"
## [7] "dplyr" "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [13] "tidyverse" "stats" "graphics" "grDevices" "utils" "datasets"
## [19] "methods" "base"
##
## [[5]]
## [1] "modelsummary" "fst" "broom" "infer" "lubridate"
## [6] "forcats" "stringr" "dplyr" "purrr" "readr"
## [11] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [16] "graphics" "grDevices" "utils" "datasets" "methods"
## [21] "base"
##
## [[6]]
## [1] "effects" "carData" "modelsummary" "fst" "broom"
## [6] "infer" "lubridate" "forcats" "stringr" "dplyr"
## [11] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [16] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [21] "datasets" "methods" "base"
##
## [[7]]
## [1] "survey" "survival" "Matrix" "grid" "effects"
## [6] "carData" "modelsummary" "fst" "broom" "infer"
## [11] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [16] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [21] "stats" "graphics" "grDevices" "utils" "datasets"
## [26] "methods" "base"
##
## [[8]]
## [1] "interactions" "survey" "survival" "Matrix" "grid"
## [6] "effects" "carData" "modelsummary" "fst" "broom"
## [11] "infer" "lubridate" "forcats" "stringr" "dplyr"
## [16] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [21] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [26] "datasets" "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")# 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$trust, na.rm = TRUE, to=c(100,0))ggplot(sweden_data, aes(x = populist)) +
geom_histogram(bins = 30, fill = "blue", color = "black") +
theme_minimal() +
labs(title = "Distribution of Populist Scale for Sweden",
x = "Populist Scale",
y = "Count")## Warning: Removed 2503 rows containing non-finite values (`stat_bin()`).
## What to note about in task 1 that the largest count is 2000 when the
populist scale is at about 49. along with this it displays as a bell
curve on a graph, which is an illustration of a normal data
distribution. With a high of almost 50% on the populist scale, the
majority of the data is in the middle percentile.
Task 2
Run a linear regression with populist attitudes as the outcome, educational attainment (recoded as a binary “BA or more” and “No BA”), and using the Swedish data. Print the intercept and coefficients only and interpret. Then do a tidy model table displaying the p-value (with digits = 3) and interpret.
sweden_data <- read.fst("sweden_data.fst")Sf <- read.fst("Sweden_data.fst")
Sf <- Sf %>%
mutate(
behave = ipbhprp,
secure = impsafe,
safety = ipstrgv,
tradition = imptrad,
rules = ipfrule
) %>%
mutate(across(c(behave, secure, safety, tradition, rules),
~ na_if(.x, 7) %>% na_if(8) %>% na_if(9))) %>%
mutate(across(c(behave, secure, safety, tradition, rules), ~ 7 - .x )) %>%
mutate(
populist = scales::rescale(behave + secure + safety + tradition + rules, to=c(0,100), na.rm=TRUE)
)
Sf <- Sf %>% filter(!is.na(populist))
model_data <- Sf %>%
mutate(
educ.ba = case_when(
essround < 5 & edulvla == 5 ~ "BA or more",
essround >= 5 & edulvlb > 600 ~ "BA or more",
TRUE ~ "No BA"
),
educ.ba = factor(educ.ba, levels = c("No BA", "BA or more"))
)
table (model_data$educ.ba)##
## No BA BA or more
## 10625 3703model1 <- lm(populist ~ educ.ba, data = model_data)coefficients_sweden <- coef(model1)
print(coefficients_sweden)## (Intercept) educ.baBA or more
## 58.04499 -4.73686tidy(model1)## # A tibble: 2 × 5
## term estimate std.error statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 58.0 0.169 343. 0
## 2 educ.baBA or more -4.74 0.332 -14.2 9.66e-46tidy(model1) |>
knitr::kable(digits = 3)| term | estimate | std.error | statistic | p.value |
|---|---|---|---|---|
| (Intercept) | 58.045 | 0.169 | 343.400 | 0 |
| educ.baBA or more | -4.737 | 0.332 | -14.247 | 0 |
Interpretation
Intercept (58.04): This represents the estimated value of populist attitudes when all other predictors are zero. In this case, it likely means the estimated level of populist attitudes among individuals with no BA education (assuming this is the reference category for educational attainment) and when other variables are at their reference levels.
Educational Attainment (BA or more) Coefficient (-4.73): This indicates the estimated change in populist attitudes for individuals who have a BA education or higher compared to those who do not, holding all other variables constant. A negative coefficient suggests that individuals with a higher level of education tend to have lower levels of populist attitudes compared to those with lower education levels.
The p-value for the intercept and the coefficient for educational attainment (BA or more) is 0.000, indicating that both coefficients are statistically significant at the 0.05 significance level. This means that both the intercept (58.04) and the coefficient for educational attainment (BA or more) (-4.73) are unlikely to have occurred by chance, suggesting a meaningful relationship between these variables and populist attitudes in the Swedish data.
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")
## 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$secure)##
## 1 2 3 4 5 6
## 54 139 626 1856 2876 2881table(df$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$essround == i] <- replacements[i]
}
auth_avg <- df %>%
group_by(year) %>%
summarize(auth_avg = mean(auth, na.rm = TRUE))
plot_auth <- ggplot(auth_avg, aes(x = year, y = auth_avg)) +
geom_point(aes(color = auth_avg), alpha = 1.0) +
geom_line(aes(group = 1), color = "blue", linetype = "dashed") +
labs(title = "Authoritarian Scale Average by Year (Italy)",
x = "Survey Year",
y = "Authoritarian Scale Average") +
theme_minimal() +
theme(legend.position = "none") +
scale_y_continuous(limits = c(0, 100))
print(plot_auth)
Interpretation for task 3
base off of the graph you can see that the data has steady and continuous throught the survey years with the authoritarian scale average being 75 in 2012 and about 74 from 2016-2020
Task 4
Now run a linear regression model, using the modelsummary package, with authoritarian values as the outcome, and generations as the predictor/potential explanatory variable, and using the Italian data again. Rename the coefficients using the coef_rename function. Interpret the coefficients, whether they are statistically significant, and the adjusted R-squared.
model_data <- df %>%
mutate(
# Recoding age, setting 999 to NA
age = ifelse(agea == 999, NA, agea),
# Recoding cohort variable, setting years before 1930 and after 2000 to NA
cohort = ifelse(yrbrn < 1930 | yrbrn > 2000, NA, yrbrn),
# Recoding generational cohorts based on year of birth
gen = case_when(
yrbrn %in% 1900:1945 ~ "1",
yrbrn %in% 1946:1964 ~ "2",
yrbrn %in% 1965:1979 ~ "3",
yrbrn %in% 1980:1996 ~ "4",
TRUE ~ as.character(cohort) # Keeping other values as character if they do not fit the ranges
),
# Converting cohort to a factor with labels
gen = factor(gen,
levels = c("1", "2", "3", "4"),
labels = c("Interwar", "Baby Boomers", "Gen X", "Millennials"))
)
table(model_data$gen)##
## Interwar Baby Boomers Gen X Millennials
## 1026 2580 2214 1811model1<- lm(auth ~ gen, data = model_data)modelsummary(
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 |
models <- list(
"model 1" = lm(auth ~ gen, data = model_data))
modelsummary(models, fmt = 1,
estimate = c("{estimate} ({std.error}){stars}"),
statistic = NULL,
coef_rename = c("genBaby Boomers" = "Baby Boomers", "genGen X" = "Gen X", "genMillennials" = "Millennials"),
title = 'Table 2. Regression models for authoritarian attitudes')| model 1 | |
|---|---|
| (Intercept) | 75.3 (0.5)*** |
| Baby Boomers | −1.1 (0.6)* |
| Gen X | −2.1 (0.6)*** |
| Millennials | −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 |
coefficients Interpretation:
genBaby Boomers is -1.1 it signifies less than interwar. leading tp Gen X being -2.1 and is lower than interwar. while genMillennials is -3.6. lastly R-squared before adjustment is 0.006 and after adjustment it is still the same meaning it is unchanged
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")# 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
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$trstprt)
# Creating and rescaling the trust variable
greece_data$trust <- scales::rescale(greece_data$trstplt + greece_data$trstprl + greece_data$trstprt, na.rm = TRUE, to = c(0, 100))
# Here's how you would "flip it" because populist is conceived by N + I as 'anti-trust'
# As Schafer explains there are some issues with that conceptualization, but N + I is also widely applied
greece_data$populist <- scales::rescale(greece_data$trust, na.rm = TRUE, to=c(100,0))model_data <- greece_data %>%
mutate(
ID = case_when(
lrscale %in% 0:4 ~ "Left", # This time: Values 0 to 3 in 'lrscale' are categorized as "Left"
lrscale %in% 6:10 ~ "Right", # This time: Values 6 to 10 in 'lrscale' are categorized as "Right"
lrscale %in% c(77, 88, 99) ~ NA_character_, # Values 77, 88, 99 in 'lrscale' are set as NA
TRUE ~ NA_character_ # Any other values not explicitly matched above
),
# Recoding gender
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
gndr == 9 ~ NA_character_,
TRUE ~ as.character(gndr)
), # Recoding age, setting 999 to NA
age = ifelse(agea == 999, NA, agea),
# Recoding cohort variable, setting years before 1930 and after 2000 to NA
cohort = ifelse(yrbrn < 1930 | yrbrn > 2000, NA, yrbrn),
# Recoding generational cohorts based on year of birth
gen = case_when(
yrbrn %in% 1900:1945 ~ "1",
yrbrn %in% 1946:1964 ~ "2",
yrbrn %in% 1965:1979 ~ "3",
yrbrn %in% 1980:1996 ~ "4",
TRUE ~ as.character(cohort) # Keeping other values as character if they do not fit the ranges
),
# Converting cohort to a factor with labels
gen = factor(gen,
levels = c("1", "2", "3", "4"),
labels = c("Interwar", "Baby Boomers", "Gen X", "Millennials"))
)
table(model_data$gen)##
## Interwar Baby Boomers Gen X Millennials
## 2978 3484 3498 2330Interpretation
Generational Differences: There seems to be a variation in populist attitudes across different generations. Baby Boomers, Generation X, and the Interwar generation appear to have higher scores on the populist attitudes scale compared to Millennials. This suggests that older generations tend to exhibit more populist attitudes compared to younger generations in Greece.
model1 <- lm(populist ~ ID , data = model_data)
model2 <- lm(populist ~ gndr, data = model_data)
model3 <- lm(populist ~ gen, data = model_data)models <- list(
"Model 1" = lm(populist ~ ID, 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)| Model 1 | Model 2 | Model 3 | |
|---|---|---|---|
| (Intercept) | 72.0 (0.5)*** | 70.0 (0.3)*** | 65.8 (0.5)*** |
| IDRight | −8.8 (0.6)*** | ||
| gndrMale | −1.0 (0.5)* | ||
| genBaby Boomers | 3.5 (0.7)*** | ||
| genGen X | 5.6 (0.7)*** | ||
| genMillennials | 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')
models <- list(
"Model 1" = lm(populist ~ ID, 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("ID" = "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)*** |
| IDRight | −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 |