Packages

Remember: you always need to do this step first and include all the packages you need

packages <- c("tidyverse", "fst", "modelsummary", "viridis") # add any you need here

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
## Loading required package: viridisLite
## [[1]]
##  [1] "lubridate" "forcats"   "stringr"   "dplyr"     "purrr"     "readr"    
##  [7] "tidyr"     "tibble"    "ggplot2"   "tidyverse" "stats"     "graphics" 
## [13] "grDevices" "utils"     "datasets"  "methods"   "base"     
## 
## [[2]]
##  [1] "fst"       "lubridate" "forcats"   "stringr"   "dplyr"     "purrr"    
##  [7] "readr"     "tidyr"     "tibble"    "ggplot2"   "tidyverse" "stats"    
## [13] "graphics"  "grDevices" "utils"     "datasets"  "methods"   "base"     
## 
## [[3]]
##  [1] "modelsummary" "fst"          "lubridate"    "forcats"      "stringr"     
##  [6] "dplyr"        "purrr"        "readr"        "tidyr"        "tibble"      
## [11] "ggplot2"      "tidyverse"    "stats"        "graphics"     "grDevices"   
## [16] "utils"        "datasets"     "methods"      "base"        
## 
## [[4]]
##  [1] "viridis"      "viridisLite"  "modelsummary" "fst"          "lubridate"   
##  [6] "forcats"      "stringr"      "dplyr"        "purrr"        "readr"       
## [11] "tidyr"        "tibble"       "ggplot2"      "tidyverse"    "stats"       
## [16] "graphics"     "grDevices"    "utils"        "datasets"     "methods"     
## [21] "base"

Task 1

Provide code and answer.

Prompt: in the tutorial, we calculated the average trust in others for France and visualized it. Using instead the variable ‘Trust in Parliament’ (trstplt) and the country of Spain (country file provided on course website), visualize the average trust by survey year. You can truncate the y-axis if you wish. Provide appropriate titles and labels given the changes. What are your main takeaways based on the visual (e.g., signs of increase, decrease, or stall)?

spain_data <- read.fst("spain_data.fst")
spain_data <- spain_data %>%
  mutate(
    trstplt = ifelse(trstplt %in% c(77, 88, 99), NA, trstplt), 
  )
table(spain_data$trstplt)
## 
##    0    1    2    3    4    5    6    7    8    9   10 
## 5165 1830 2329 2441 2085 2890 1154  639  355   80   71
spain_data$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
  spain_data$year[spain_data$essround == i] <- replacements[i]
}
table(spain_data$year)
## 
## 2002 2004 2006 2008 2010 2012 2014 2016 2018 2020 
## 1729 1663 1876 2576 1885 1889 1925 1958 1668 2283
trust_by_year <- spain_data %>%
  group_by(year) %>%
  summarize(mean_trust = mean(trstplt, na.rm = TRUE))
trust_by_year
## # A tibble: 10 × 2
##     year mean_trust
##    <dbl>      <dbl>
##  1  2002       3.41
##  2  2004       3.66
##  3  2006       3.49
##  4  2008       3.32
##  5  2010       2.72
##  6  2012       1.91
##  7  2014       2.23
##  8  2016       2.40
##  9  2018       2.55
## 10  2020       1.94
ggplot(trust_by_year, aes(x = year, y = mean_trust)) +
  geom_line(aes(group = 1), color = "purple", size = 1, linetype = "longdash") +  
  geom_point(aes(color = mean_trust), size = 3) +  
  scale_color_viridis(option = "D", end = 0.9, direction = -1) +  
  labs(title = "Trust in Spanish Parliament (2002-2020)", 
       x = "Survey Year", 
       y = "Average Trust (0-10 scale)") +
  ylim(0, 10) +  
  theme_minimal() +  
  theme(legend.position = "none")  
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

## Therefore, We can conclude that from 2002 - 2012, citizens trust in the Spanish parliament was on the decline. However, from 2012 - 2018, the trust in the Spanish parliament increased, but would once again decrease come 2020.

Task 2

Provide answer only.

Prompt and question: Based on the figure we produced above called task2_plot, tell us: what are your main takeaways regarding France relative to Italy and Norway? Make sure to be concrete and highlight at least two important comparative trends visualized in the graph.

France and the other countries are relatively following a decline in closeness to a party by cohort. Initially, looking at this graph, from the 1920’s to the 1950’s all the countries are stagnant and sort of stall, feeling close to a party by cohort.However from the 1960’s to the 1990’s, the proportion of those who say “yes” to feeling close to a party by cohort was on the decline.

Task 3

Provide code and answer.

Question: What is the marginal percentage of Italian men who feel close to a particular political party?

italy_data <- read.fst("italy_data.fst")
italy_data <- italy_data %>%
  mutate(
    gndr = case_when(
      gndr == 1 ~ "Male",
      gndr == 2 ~ "Female",
      TRUE ~ NA_character_  
    ),
    clsprty  = case_when(
      clsprty  %in% 1 ~ "Yes",       
      clsprty  %in% 2 ~ "No",     
      TRUE ~ NA_character_  
    )    
  ) 
clsprty_percentages <- italy_data %>%  
  filter(!is.na(clsprty), !is.na(gndr)) %>%  
  group_by(gndr, clsprty) %>%  
  summarise(count = n(), .groups = 'drop') %>%  
  mutate(percentage = count / sum(count) * 100)  

clsprty_percentages  
## # A tibble: 4 × 4
##   gndr   clsprty count percentage
##   <chr>  <chr>   <int>      <dbl>
## 1 Female No       3228       34.2
## 2 Female Yes      1686       17.9
## 3 Male   No       2593       27.5
## 4 Male   Yes      1936       20.5

Therefore, the marginal percentage of Italian men who feel close to a particular political party is 20.50196%.

Task 4

Provide code and output only.

Prompt: In the tutorial, we calculated then visualized the percentage distribution for left vs. right by gender for France. Your task is to replicate the second version of the visualization but for the country of Sweden instead.

sweden_data <- read.fst("sweden_data.fst")
sweden_data <- sweden_data %>%
  mutate(
    gndr = case_when(
      gndr == 1 ~ "Male",
      gndr == 2 ~ "Female",
      TRUE ~ NA_character_  
    ),
    lrscale = case_when(
      lrscale %in% 0:3 ~ "Left",       
      lrscale %in% 7:10 ~ "Right",    
      TRUE ~ NA_character_  
    )    
  ) 
lrscale_percentages <- sweden_data %>%  
  filter(!is.na(lrscale), !is.na(gndr)) %>%  
  group_by(gndr, lrscale) %>%  
  summarise(count = n(), .groups = 'drop') %>%  
  mutate(percentage = count / sum(count) * 100)  

lrscale_percentages  
## # A tibble: 4 × 4
##   gndr   lrscale count percentage
##   <chr>  <chr>   <int>      <dbl>
## 1 Female Left     2296       23.0
## 2 Female Right    2530       25.3
## 3 Male   Left     2062       20.6
## 4 Male   Right    3107       31.1
lrscale_plot <- ggplot(lrscale_percentages, aes(x = lrscale, y = percentage, fill = lrscale)) +
  geom_bar(stat = "identity", position = position_dodge()) +  
  facet_wrap(~ gndr, scales = "fixed") +  
  scale_fill_brewer(palette = "Set1") +  
  labs(
    title = "Political Orientation (Left vs. Right) by Gender in Sweden",
    x = "Political Orientation",
    y = "Percentage of Respondents",
    fill = "Orientation"
  ) +
  theme_minimal() +  # Minimal theme for clarity
  theme(legend.position = "bottom")  
lrscale_plot

## Task 5

Provide code and answer: In Hungary, what is the conditional probability of NOT feeling close to any particular party given that the person lives in a rural area?

hungary_data <- read.fst("hungary_data.fst")
hungary_data <- hungary_data %>%
  mutate(
    geo = recode(as.character(domicil), 
                 '1' = "Urban", 
                 '2' = "Urban",
                 '3' = "Rural", 
                 '4' = "Rural", 
                 '5' = "Rural",
                 '7' = NA_character_,
                 '8' = NA_character_,
                 '9' = NA_character_)
  ) %>%
  filter(!is.na(clsprty), !is.na(geo))
hungary_data <- hungary_data %>%
  mutate(
    clsprty  = case_when(
      clsprty  %in% 1 ~ "Yes",       
      clsprty  %in% 2 ~ "No",    
      TRUE ~ NA_character_  
    ) 
  ) %>%
      
  filter(!is.na(clsprty))
cond <- hungary_data %>%
  count(clsprty, geo) %>%
  group_by(geo) %>%
  mutate(prob = n / sum(n)*100)

cond
## # A tibble: 4 × 4
## # Groups:   geo [2]
##   clsprty geo       n  prob
##   <chr>   <chr> <int> <dbl>
## 1 No      Rural  6275  55.4
## 2 No      Urban  2395  51.2
## 3 Yes     Rural  5055  44.6
## 4 Yes     Urban  2283  48.8

Therefore, In Hungary, the conditional probability of those not feeling close to any particular party of those who live in rural areas is 55.38394%.