R Markdown

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:

sweden_data <- read.fst("sweden_data.fst")
## Warning: package 'fstcore' was built under R version 4.3.3
# 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()`).

Task 1: For the populist scale at around 50/51 theres a much higher count/peak that’s slighty higher then 2000, then after 50 there seems to be a decline in the count.

sweden_data <- sweden_data %>%
  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(sweden_data$gen)
## 
##     Interwar Baby Boomers        Gen X  Millennials 
##         4021         5787         4263         3609
sweden_data <- sweden_data %>%
  mutate(
    ID = case_when(
      lrscale %in% 0:4 ~ "Left",                     # This time: Values 0 to 3 in 'lrscale' are categorized as "Left"
      lrscale %in% 6:10 ~ "Right",                   # This time: Values 6 to 10 in 'lrscale' are categorized as "Right"
      lrscale %in% c(77, 88, 99) ~ NA_character_,    # Values 77, 88, 99 in 'lrscale' are set as NA
      TRUE ~ NA_character_                           # Any other values not explicitly matched above
    )
  )
table(sweden_data$ID)
## 
##  Left Right 
##  6188  7406
sweden_pop_model <- lm(populist ~ ID, data = sweden_data)

coefficients_sweden <- coef(sweden_pop_model)
print(coefficients_sweden)
## (Intercept)     IDRight 
##  48.3188406  -0.7149274
tidy(sweden_pop_model)
## # A tibble: 2 × 5
##   term        estimate std.error statistic p.value
##   <chr>          <dbl>     <dbl>     <dbl>   <dbl>
## 1 (Intercept)   48.3       0.265    183.    0     
## 2 IDRight       -0.715     0.356     -2.01  0.0444
tidy(sweden_pop_model) |>
knitr::kable(digits = 3)
term estimate std.error statistic p.value
(Intercept) 48.319 0.265 182.562 0.000
IDRight -0.715 0.356 -2.011 0.044

Task 2: On top represents the expected level oif populist attitudes when educational attainment is no BA. (The reference category). The coefficient for BA represents the change in the expected level of populist attotudes when comparing individuals with BA or higher education to thoose without a BA, holding all other variables constant.P-value is statistically significant in predicting populist attitudes/outcome variable.

## 
##    1    2    3    4    5    6 
##   54  139  626 1856 2876 2881
## 
##   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

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.

Task 3: The authoritarian scale average seems to be at one position/starts at 75 and stays consistent around there through out the years 2012-2020 with a very slight change.

italy_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(italy_data$gen)
## 
##     Interwar Baby Boomers        Gen X  Millennials 
##         1026         2580         2214         1811
model1 <- lm(auth ~ gen, data = italy_data)
model2 <- lm(auth ~ gndr, data = italy_data)
model3 <- lm(auth ~ educ.ba, data = italy_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
F 15.648
RMSE 14.94

Task 4: The coefficients are statisticaly significant (the indepedent varaiable indicating political orientation and dependent variable populist scale). Adjusted R-squared measures how well the independet varaible explain the variance in the dependent variable. In this case both R squared values are relatively low showing that the model explains only a small portion of the variance in populist scale.

df <- read.fst("greece_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$secure)
## 
##    1    2    3    4    5    6 
##   44  216  548 1345 3922 6228
table(df$auth)
## 
##    0    4    8   12   16   20   24   28   32   36   40   44   48   52   56   60 
##    2    3    1    3    4   11   11   28   43   73  105  170  224  324  413  602 
##   64   68   72   76   80   84   88   92   96  100 
##  700  806 1004 1202 1449 1395 1273 1070  794  593
ggplot(df, aes(x = auth)) +
  geom_histogram(bins = 30, fill = "blue", color = "black") +
  theme_minimal() +
  labs(title = "Distribution of Authoritarian Scale for Greece",
       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 (greece)",
       x = "Survey Year",
       y = "Authoritarian Scale Average") +
  theme_minimal() +
  theme(legend.position = "none") +
  scale_y_continuous(limits = c(0, 100))

print(plot_auth)

greece_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(greece_data$gen)
## 
##     Interwar Baby Boomers        Gen X  Millennials 
##         2909         3420         3434         2279
model1 <- lm(auth ~ gen, data = greece_data)
model2 <- lm(auth ~ gndr, data = greece_data)
model3 <- lm(auth ~ educ.ba, data = greece_data)

modelsummary(
  list(model1),
  fmt = 1,
  estimate  = c( "{estimate} ({std.error}){stars}"),
  statistic = NULL,
  coef_omit = "Intercept")
 (1)
genBaby Boomers −4.1 (0.4)***
genGen X −6.0 (0.4)***
genMillennials −10.3 (0.4)***
Num.Obs. 12042
R2 0.054
R2 Adj. 0.054
AIC 98536.4
BIC 98573.4
Log.Lik. −49263.205
F 229.177
RMSE 14.47
models <- list(
   "Model 1" = lm(auth ~ gen, data = greece_data),
   "Model 2" = lm(auth ~ gndr, data = greece_data),
   "Model 3" = lm(auth ~ educ.ba, data = greece_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) 82.0 (0.3)*** 77.8 (0.2)*** 77.4 (0.2)***
genBaby Boomers −4.1 (0.4)***
genGen X −6.0 (0.4)***
genMillennials −10.3 (0.4)***
gndrMale −2.0 (0.3)***
educ.baBA or more −2.4 (0.3)***
Num.Obs. 12042 12303 12303
R2 0.054 0.005 0.004
R2 Adj. 0.054 0.004 0.004
AIC 98536.4 101489.4 101493.3
BIC 98573.4 101511.7 101515.6
Log.Lik. −49263.205 −50741.707 −50743.669
F 229.177 55.687 51.745
RMSE 14.47 14.96 14.96
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", "educ.baBA or more" = "BA or More"),
  title = 'Table 2. Regression models for authoritarian attitudes')
Table 2. Regression models for authoritarian attitudes
Model 1  Model 2  Model 3
(Intercept) 82.0 (0.3)*** 77.8 (0.2)*** 77.4 (0.2)***
Baby Boomers −4.1 (0.4)***
Gen X −6.0 (0.4)***
Millennials −10.3 (0.4)***
Male −2.0 (0.3)***
BA or More −2.4 (0.3)***
Num.Obs. 12042 12303 12303
R2 0.054 0.005 0.004
R2 Adj. 0.054 0.004 0.004
AIC 98536.4 101489.4 101493.3
BIC 98573.4 101511.7 101515.6
Log.Lik. −49263.205 −50741.707 −50743.669
F 229.177 55.687 51.745
RMSE 14.47 14.96 14.96

Task 5: For the authoritarian scale for Greece there seems to be a slight decline throughout the years from 2005-2020.The distribution scale for Greece there’s a increase in the authoritarian scale from around 55/60 till 77 and then a decline.