This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)
## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.
#Installing & Applying Packages
packages <-c("tidyverse", "modelsummary", "flextable", "fst", "viridis", "knitr", "effects", "rmarkdown", "survey", "interactions", "infer", "broom")
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 1.1.4 ✔ 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
##
## Attaching package: 'flextable'
##
##
## The following object is masked from 'package:purrr':
##
## compose
##
##
## Loading required package: viridisLite
##
## 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
##
##
## Registered S3 methods overwritten by 'broom':
## method from
## tidy.glht jtools
## tidy.summary.glht jtools
## [[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] "flextable" "modelsummary" "lubridate" "forcats" "stringr"
## [6] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [11] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [16] "utils" "datasets" "methods" "base"
##
## [[4]]
## [1] "fst" "flextable" "modelsummary" "lubridate" "forcats"
## [6] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [11] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [16] "grDevices" "utils" "datasets" "methods" "base"
##
## [[5]]
## [1] "viridis" "viridisLite" "fst" "flextable" "modelsummary"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[6]]
## [1] "knitr" "viridis" "viridisLite" "fst" "flextable"
## [6] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [11] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [16] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [21] "datasets" "methods" "base"
##
## [[7]]
## [1] "effects" "carData" "knitr" "viridis" "viridisLite"
## [6] "fst" "flextable" "modelsummary" "lubridate" "forcats"
## [11] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [16] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [21] "grDevices" "utils" "datasets" "methods" "base"
##
## [[8]]
## [1] "rmarkdown" "effects" "carData" "knitr" "viridis"
## [6] "viridisLite" "fst" "flextable" "modelsummary" "lubridate"
## [11] "forcats" "stringr" "dplyr" "purrr" "readr"
## [16] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [21] "graphics" "grDevices" "utils" "datasets" "methods"
## [26] "base"
##
## [[9]]
## [1] "survey" "survival" "Matrix" "grid" "rmarkdown"
## [6] "effects" "carData" "knitr" "viridis" "viridisLite"
## [11] "fst" "flextable" "modelsummary" "lubridate" "forcats"
## [16] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [21] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [26] "grDevices" "utils" "datasets" "methods" "base"
##
## [[10]]
## [1] "interactions" "survey" "survival" "Matrix" "grid"
## [6] "rmarkdown" "effects" "carData" "knitr" "viridis"
## [11] "viridisLite" "fst" "flextable" "modelsummary" "lubridate"
## [16] "forcats" "stringr" "dplyr" "purrr" "readr"
## [21] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [26] "graphics" "grDevices" "utils" "datasets" "methods"
## [31] "base"
##
## [[11]]
## [1] "infer" "interactions" "survey" "survival" "Matrix"
## [6] "grid" "rmarkdown" "effects" "carData" "knitr"
## [11] "viridis" "viridisLite" "fst" "flextable" "modelsummary"
## [16] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [21] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [26] "stats" "graphics" "grDevices" "utils" "datasets"
## [31] "methods" "base"
##
## [[12]]
## [1] "broom" "infer" "interactions" "survey" "survival"
## [6] "Matrix" "grid" "rmarkdown" "effects" "carData"
## [11] "knitr" "viridis" "viridisLite" "fst" "flextable"
## [16] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [21] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [26] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [31] "datasets" "methods" "base"
#Import dataset
rm(list=ls()); gc()
## used (Mb) gc trigger (Mb) limit (Mb) max used (Mb)
## Ncells 2660243 142.1 4290552 229.2 NA 4290552 229.2
## Vcells 4537246 34.7 10146329 77.5 16384 7063936 53.9
hungary_data <-read.fst("hungary_data.fst")
italy_data <- read.fst("italy_data.fst")
greece_data <-read.fst("greece_data.fst")
sweden_data<-read.fst("sweden_data.fst")
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$trust, na.rm = TRUE, to=c(100,0))
ggplot(sweden_data, aes(x = populist)) +
geom_histogram(bins = 30, fill = "pink", color = "black") +
theme_minimal() +
labs(title = "Distribution of Populist Scale for Sweden",
x = "Populist Scale",
y = "Count")
## Warning: Removed 2503 rows containing non-finite values (`stat_bin()`).
Response:
The data on the the graph aappears to be more right skewed indicating a postitve trend. This meaning that the inviduals have a lower level of populism resulting in a higer trust in parliament.
Run a linear regression with populist attitudes as the outcome, educational attainment (recoded as a binary “BA or more” and “No BA”), and using the Swedish data. Print the intercept and coefficients only and interpret. Then do a tidy model table displaying the p-value (with digits = 3) and interpret.
# New dataframe for sweden data called dfs
dfs <- read.fst("sweden_data.fst")
dfs <- dfs %>%
mutate(
trstplt = ifelse(dfs$trstplt > 10, NA, dfs$trstplt),
trstprl = ifelse(dfs$trstprl > 10, NA, dfs$trstprl),
trstprt = ifelse(dfs$trstprt > 10, NA, dfs$trstprt))
# Creating and rescaling the trust variable
dfs$trust <-scales::rescale(dfs$trstplt + dfs$trstprl + dfs$trstprt, na.rm = TRUE, to=c(0,100))
# Rescale trust to create populist scale
dfs$populist <-scales::rescale(dfs$trust, na.rm=TRUE, to=c(100,0))
#Recoding education variable
dfs <- dfs %>%
mutate(
educ.ba = case_when(
essround < 5 & edulvla == 5 ~ "BA or more",
essround >= 5 & edulvlb > 600 ~ "BA or more",
TRUE ~ "No BA"),
#Recoding specific values to NA
edulvla = ifelse(edulvla %in% c(77, 88, 99), NA_integer_, edulvla),
edulvlb = ifelse(edulvlb %in% c(5555, 7777, 8888), NA_integer_, edulvlb),
#Converting educ.ba to a factor with specified levels
educ.ba = factor(educ.ba, levels = c("No BA", "BA or more")))
#Coefficients & Intercept
model<-lm(dfs$populist ~educ.ba, data = dfs)
coefficients_dfs <-coef(model)
print(coefficients_dfs)
## (Intercept) educ.baBA or more
## 51.358680 -7.868121
tidy(model) |>
knitr::kable(digits = 3)
| term | estimate | std.error | statistic | p.value |
|---|---|---|---|---|
| (Intercept) | 51.359 | 0.181 | 283.363 | 0 |
| educ.baBA or more | -7.868 | 0.350 | -22.494 | 0 |
when comparing people in Sweden who have a Bachelor’s degree or higher to those who do not, we anticipate the average populist scale score to be 7.9 points lower for the former group. This indicates that people without a BA show more populist attitudes compared to those with a BA or higher education
Intercept (51.4): The reference group in Sweden has an average score of 51.4 on the populist scale, indicating that the expected average populist score is also 51.4. This score shows a specific degree of populism, with higher scores indicating more pronounced populist beliefs.
educ.baBA (-7.9) Coefficient: The BA or more group has a negative coefficient of -7.9, showing that individuals with a BA or higher in Sweden, on average, have populist scores 7.9 points lower than those without a BA (according to our recode).
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")
#new dataframe with italy data called dfi
dfi<-read.fst("italy_data.fst")
#create authoritarian values scale based on human modules items
dfi <-dfi %>%
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))
#calculate autho after NA recoding
dfi$auth <-scales::rescale(dfi$behave +
dfi$secure +
dfi$safety +
dfi$tradition +
dfi$rules, to=c(0,100), na.rm=TRUE )
dfi <-dfi %>% filter(!is.na(auth))
table(dfi$secure)
##
## 1 2 3 4 5 6
## 54 139 626 1856 2876 2881
table(dfi$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
## 632 465 299 297
#Looking at the year-by-year average for authoritarian scale
dfi$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
dfi$year[dfi$essround == i] <- replacements[i]}
auth_avg <- dfi %>%
group_by(year) %>%
summarize(auth_avg = mean(auth, na.rm = TRUE))
# Visualizing distribution before proceeding
ggplot(dfi, aes(x = auth)) +
geom_histogram(bins = 30, fill = "pink", color = "black") +
theme_minimal() +
labs(title = "Distribution of Authoritarian Scale for Italy",
x = "Authoritarian Scale",
y = "Count")
#Graphing authoritarian values by year for Italy
plot_auth <- ggplot(auth_avg, aes(x = year, y = auth_avg)) +
geom_point(aes(color = auth_avg), alpha = 1.0) +
geom_line(aes(group = 1), color = "pink", linetype = "dashed") +
labs(title = "Authoritarian Scale Average by Year (Italy)",
x = "Survey Year",
y = "Authoritarian Scale Average") +
theme_minimal() +
theme(legend.position = "none") +
scale_y_continuous(limits = c(0, 100))
print(plot_auth)
The average authoritarian scale for Italy has remained relatively stable
over time with minimal fluctuations. From 2012 to 2016, there was a
slight decrease in a fluctuation, followed by a relatively stable trend
from 2016 to 2020.
Now run a linear regression model, using the modelsummary package, with authoritarian values as the outcome, and generations as the predictor/potential explanatory variable, and using the Italian data again. Rename the coefficients using the coef_rename function. Interpret the coefficients, whether they are statistically significant, and the adjusted R-squared.
#New dataframe called italy_regress
italy_regress<-dfi %>%
mutate(
cohort = ifelse(yrbrn < 1930 | yrbrn > 2000, NA, yrbrn),
gen=case_when(
yrbrn %in% 1900:1945 ~ "1",
yrbrn %in% 1946:1964 ~ "2",
yrbrn %in% 1965:1979 ~ "3",
yrbrn %in% 1980:1996 ~ "4",
TRUE ~ as.character(cohort)),
gen=factor(gen,
levels = c("1", "2", "3", "4"),
labels = c("Interwar", "Baby Boomers", "Gen X", "Millennials")))
table(italy_regress$gen)
##
## Interwar Baby Boomers Gen X Millennials
## 1026 2580 2214 1811
#Running linear regression model
italy_model <- lm(auth ~ gen, data = italy_regress)
#Renamed coefficients & viewing table
modelsummary(
list(italy_model),
fmt = 1,
estimate = c( "{estimate} ({std.error}){stars}"),
statistic = NULL,
coef_omit = "Intercept",
coef_rename = c("genBaby Boomers" = "Baby Boomers", "genGen X" = "Gen X", "genMillennials" = "Millennials"),
title = 'Regression model for authoritarian attitudes in Italy')
| (1) | |
|---|---|
| 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 |
Baby Boomers showed a statistically significant 1.1 point decrease on the authoritarian values scale compared to the Interwar generation. The use of a single asterisk () indicates statistical significance at a p-value of 0.05, which is our alpha threshold. GenX exhibits a further decline, scoring 2.1 points lower than the Interwar generation on the authoritarian values scale (p<0.001). Three asterisks () indicate statistical significance with a p-value of 0.001, which is lower than our alpha level of 0.05. Millennials exhibit the most significant decline in authoritarian values, registering 3.6 points lower scores than the Interwar generation (p<0.001). This value is indicated by three asterisks (*), showing statistical significance with a low p-value of 0.001, below our alpha level of 0.05. Adjusted R-Squared (Adj. R^2 = 0.006): With an adjusted R-squared value of 0.006, the ‘gen’ variable accounts for about 0.6% of the variability in the authoritarian values scale for Italy, considering the predictors. Although statistically significant, this indicates that the model accounts for only a small portion of the variance in authoritarian values, indicating that there are other factors besides generational differences that could be crucial in influencing these attitudes
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.
#new dataframe called dfg
dfg<-read.fst("greece_data.fst")
# Populist scale (Norris/Inglehart use low levels of trust in parliaments, politicians and parties as an indicator of populism). Higher=anti-trust
# Setting values greater than 10 to NA
dfg$trstplt <- ifelse(dfg$trstplt > 10, NA, dfg$trstplt)
dfg$trstprl <- ifelse(dfg$trstprl > 10, NA, dfg$trstprl)
dfg$trstprt <- ifelse(dfg$trstprt > 10, NA, dfg$trstprt)
# Creating and rescaling the trust variable
dfg$trust <-scales::rescale(dfg$trstplt + dfg$trstprl + dfg$trstprt, na.rm = TRUE, to=c(0,100))
#Rescale trust to create populist scale
dfg$populist <-scales::rescale(dfg$trust, na.rm=TRUE, to=c(100,0))
#Recoding lrscale, gndr, & gen variables
dfg<-dfg %>%
mutate(
lrscale = case_when(
lrscale %in% 0:4 ~ "Left",
lrscale %in% 6:10 ~ "Right", #Note: 5 set to NA because its "Moderate"
lrscale %in% c(77, 88, 99) ~NA_character_,
TRUE ~ NA_character_),
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
gndr == 9 ~ NA_character_,
TRUE ~ as.character(gndr)),
cohort = ifelse(yrbrn < 1930 | yrbrn > 2000, NA, yrbrn),
gen=case_when(
yrbrn %in% 1900:1945 ~ "1",
yrbrn %in% 1946:1964 ~ "2",
yrbrn %in% 1965:1979 ~ "3",
yrbrn %in% 1980:1996 ~ "4",
TRUE ~ as.character(cohort)),
gen=factor(gen,
levels = c("1", "2", "3", "4"),
labels = c("Interwar", "Baby Boomers", "Gen X", "Millennials")))%>%
filter(!is.na(lrscale) & !is.na(gndr))
table(dfg$gen)
##
## Interwar Baby Boomers Gen X Millennials
## 1549 1847 1664 1036
#Running linear regression models
model1 <- lm(dfg$populist ~ lrscale, data = dfg)
model2 <- lm(dfg$populist ~ gndr, data = dfg)
model3 <- lm(dfg$populist ~ gen, data = dfg)
#Create models list to display all three models in the same table and later graph
models <- list(
"Model 1" = lm(dfg$populist ~ lrscale, data = dfg),
"Model 2" = lm(dfg$populist ~ gndr, data = dfg),
"Model 3" = lm(dfg$populist ~ gen, data = dfg))
#View models in a table
modelsummary(models, fmt = 1,
estimate = c("{estimate} ({std.error}){stars}",
"{estimate} ({std.error}){stars}",
"{estimate} ({std.error}){stars}"),
statistic = NULL,
coef_rename = c("genBaby Boomers" = "Baby Boomers", "genGen X" = "Gen X", "genMillennials" = "Millennials", "gndrMale" = "Male", "lrscaleRight" = "Right"),
title = 'Regression models for populist attitudes for Greece')
| Model 1 | Model 2 | Model 3 | |
|---|---|---|---|
| (Intercept) | 72.0 (0.5)*** | 67.7 (0.5)*** | 63.0 (0.7)*** |
| Right | −8.8 (0.6)*** | ||
| Male | −1.2 (0.7)+ | ||
| Baby Boomers | 3.9 (0.9)*** | ||
| Gen X | 6.8 (0.9)*** | ||
| Millennials | 6.4 (1.0)*** | ||
| Num.Obs. | 4936 | 4936 | 4822 |
| R2 | 0.037 | 0.001 | 0.013 |
| R2 Adj. | 0.036 | 0.000 | 0.012 |
| AIC | 44723.8 | 44904.5 | 43832.6 |
| BIC | 44743.3 | 44924.1 | 43865.0 |
| Log.Lik. | −22358.894 | −22449.275 | −21911.303 |
| RMSE | 22.44 | 22.85 | 22.76 |
#Visualize the coefficients & 95% confidence interval
modelplot(models, coef_omit = 'Interc')
Model 1 indicates a significant statistical difference for lrscale, with lrscale Right being approximately 9 points lower than lrscale Left on the populist value scale (ranging from 0 to 100). The orange data point, labeled lrscaleRight under Model 1, falls between -7.5 and -10 on the x-axis, representing the coefficient estimate. Model 2 does not indicate any statistical significance for the variable gndr in relation to males compared to females on the populist value scale (ranging from 0 to 100). The lack of asterisks next to the green data point, which has a coefficient of -1, shows that it is not statistically significant. The confidence interval extends horizontally from the datapoint, reaching 0 on the x-axis, indicating insignificance of the coefficient at the specified level. Model 3 indicates that Millennials, Gen X, and Baby Boomers have a higher average score on the populist value scale (ranging from 0-100) compared to the Interwar generation, as shown by the variable gen. Gen X shows the biggest rise, being the farthest right on the positive side of the x-axis, followed by Millennials and then Baby Boomers, all with confidence intervals indicating statistical significance away from the 0 line on the x-axis. The validity of this explanation is backed by coefficient values of 6.8, 6.4, and 3.9 for Gen X, Millennials, and Baby Boomers, respectively. They are all marked with three asterisks (***), showing a p-value<0.001, which is significantly lower than our alpha level of 0.05, indicating statistical significance.