# List of packages
packages <- c("tidyverse", "infer", "fst", "modelsummary", "effects", "survey", "interactions","broom") # 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 'readr' was built under R version 4.2.3
## Warning: package 'dplyr' was built under R version 4.2.3
## Warning: package 'stringr' was built under R version 4.2.3
## ── 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   3.4.4     ✔ 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
## Warning: package 'infer' was built under R version 4.2.3
## Loading required package: carData
## lattice theme set by effectsTheme()
## See ?effectsTheme for details.
## Warning: package 'survey' was built under R version 4.2.3
## 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] "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"        
## 
## [[8]]
##  [1] "broom"        "interactions" "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"

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")
## Warning: package 'fstcore' was built under R version 4.2.3
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 = "green", 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 histogram is slightly right skewed with the high levels from 0-50 on the populist scale and low levels 50 onwards on the populist scale.Furthermore there is a clear mode less than 50 as well on the populist 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 <- sweden_data %>%
  mutate(
    educ.ba = case_when(
      essround < 5 & edulvla == 5 ~ "BA or more",
      essround >= 5 & edulvlb > 600 ~ "BA or more",
      TRUE ~ "No BA"
    ),
    
    edulvla = ifelse(edulvla %in% c(77, 88, 99), NA_integer_, edulvla),
    edulvlb = ifelse(edulvlb %in% c(5555, 7777, 8888), NA_integer_, edulvlb),
    

        educ.ba = factor(educ.ba, levels = c("No BA", "BA or more"))
  )

table(sweden_data$educ.ba)
## 
##      No BA BA or more 
##      13477       4739
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         -7.868121
tidy(sweden_pop_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

A clear association between populist attitudes and educational attainment do exist

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.

library(dplyr)
library(ggplot2)
italy_data <- read.fst("italy_data.fst")

italy_data <- italy_data %>%
  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 ))


italy_data$auth <- scales::rescale(italy_data$behave + 
                      italy_data$secure + 
                      italy_data$safety + 
                      italy_data$tradition + 
                      italy_data$rules, to=c(0,100), na.rm=TRUE)


italy_data <- italy_data %>% filter(!is.na(auth))
table(italy_data$secure)
## 
##    1    2    3    4    5    6 
##   54  139  626 1856 2876 2881
table(italy_data$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
italy_data$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
  italy_data$year[italy_data$essround == i] <- replacements[i]
}
auth_avg <- italy_data %>%
  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 = "black", linetype = "dashed") +  
  labs(title = "Authoritarian Scale Average by Year (Portugal)",
       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 reduces to 73 in the year of 2016 before slightly rising till 74 between the years 2018-2020.

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 <- italy_data %>%
  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(model_data$gen)
## 
##     Interwar Baby Boomers        Gen X  Millennials 
##         1026         2580         2214         1811
model <- lm(auth ~ gen, data = model_data)
modelsummary(
  list(model),coef_rename = c("genBaby Boomers" = "Baby Boomers", "genGen X" = "Gen X", "genMillennials" = "Millennials"))
 (1)
(Intercept) 75.345
(0.467)
Baby Boomers −1.125
(0.552)
Gen X −2.080
(0.564)
Millennials −3.592
(0.584)
Num.Obs. 7631
R2 0.006
R2 Adj. 0.006
AIC 62934.0
BIC 62968.7
Log.Lik. −31462.009
RMSE 14.94

Here it i illustrated through the intercept that the avg. expected authoritarian score will ve 75.3, when all other predictable values are zero.

the co-efficient of Baby Boomers is -1.1, showcasing the authoritarian scale score being 1.1. With P almost equal to 0.05, it is not statistically significant since it is denoted by one asterisk

the co-efficient of Gen X is -2. 1, showcasing the authoritarian scale score -2.1. With P being lesser than 0.05, it is statistically significant since it is denoted by three asterisks

the co-efficient of Millenials is -3.6, showcasing that authoritarian scale score 3.6. With P being lesser than 0.05, it is statistically significant since it is denoted by three asterisks

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)
    ),
    
    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)  
    ),

  ID = case_when(
      lrscale %in% 0:3 ~ "Left",              # Values 0 to 3 in 'lrscale' are categorized as "Left"
      lrscale %in% 7:10 ~ "Right",           # Values 7 to 10 in 'lrscale' are categorized as "Right"
      #lrscale %in% 4:6 ~ "Moderate",       # Values 4 to 6 in 'lrscale' are categorized as "Moderate"
      lrscale %in% c(4,5,6,77, 88, 99) ~ NA_character_    # Values 77, 88, 99 in 'lrscale' are set as NA
    ),
    
    gen = factor(gen,
                 levels = c("1", "2", "3", "4"),
                 labels = c("Interwar", "Baby Boomers", "Gen X", "Millennials"))
  )
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) 72.4 (0.6)*** 70.0 (0.3)*** 65.8 (0.5)***
IDRight −10.5 (0.8)***
gndrMale −1.0 (0.5)*
genBaby Boomers 3.5 (0.7)***
genGen X 5.6 (0.7)***
genMillennials 5.8 (0.7)***
Num.Obs. 3480 9823 9562
R2 0.048 0.000 0.009
R2 Adj. 0.048 0.000 0.009
AIC 31648.1 88873.2 86473.9
BIC 31666.6 88894.8 86509.7
Log.Lik. −15821.063 −44433.590 −43231.944
RMSE 22.81 22.30 22.25
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) 72.4 (0.6)*** 70.0 (0.3)*** 65.8 (0.5)***
IDRight −10.5 (0.8)***
gndrMale −1.0 (0.5)*
genBaby Boomers 3.5 (0.7)***
genGen X 5.6 (0.7)***
genMillennials 5.8 (0.7)***
Num.Obs. 3480 9823 9562
R2 0.048 0.000 0.009
R2 Adj. 0.048 0.000 0.009
AIC 31648.1 88873.2 86473.9
BIC 31666.6 88894.8 86509.7
Log.Lik. −15821.063 −44433.590 −43231.944
RMSE 22.81 22.30 22.25
modelplot(models, coef_omit = 'Interc') +
    labs( title = 'Coefficients estimtates within the 95% Confidence Interval')

the Baby Boomer cohort is likely to score 3.5 higher when compared to our reference category since the co-efficient of this group is 3.5. In regards to Gen Z, a great difference from the reference category for the authoritarian score is visible, since the co-efficient of this group is 5.6. Finally for Millenials since the co-efficient is 5.8 the greatest difference can be noted when compared to the reference category on the authoritarian scale score.

Since the asterisk is three as illustrates that P is less that 0.005 this is statically significant.the variable gen only illustrates 0.9% of variance in the data according to the adjusted R value