# List of packages
packages <- c("tidyverse", "fst", "modelsummary") # 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     1.1.3     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.3     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ 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 'fst' was built under R version 4.3.2
## Warning: package 'modelsummary' was built under R version 4.3.2
## [[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"
ess <- read_fst("All-ESS-Data.fst")
## Warning: package 'fstcore' was built under R version 4.3.2

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), # set values 77, 88, and 99 to NA.
  )

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(color = "blue", size = 1) +  # Line to show the trend
  geom_point(color = "red", size = 3) +  # Points to highlight each year's value
  labs(title = "Trust in Parliament in Spain (2002-2020)", 
       x = "Survey Year", 
       y = "Average Trust (0-10 scale)") +
  ylim(0, 10) +  # Setting the y-axis limits from 0 to 10
  theme_minimal()
## 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.

Ans: The main takeway from this graph is that although there is a slight increase in trust between 2013-2018, there is an overall gradual decrease in trust in parliament.

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.

Ans: Compared to figures of Italy and Norway, France has a smaller range of values which indicates that most people are neither trustful or distrustful. Instead, they are more neutral compared to countries like Italy and Norway.

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_  # Set anything that is not 1 or 2 to NA
    ),
    lrscale = case_when(
      lrscale %in% 0:3 ~ "Left",       # Left-wing (0 to 3)
      lrscale %in% 7:10 ~ "Right",     # Right-wing (7 to 10)
      TRUE ~ NA_character_  # Moderate (4, 5, 6) and special codes (77, 88, 99) set to NA 
    ) 
  )

  lrscale_percentages <- italy_data %>%  # Begin with the dataset 'france_data'
    filter(!is.na(lrscale), !is.na(gndr)) %>%  # Filter out rows where 'lrscale' or 'gender' is NA (missing data)
    group_by(gndr, lrscale) %>%  # Group the data by 'gender' and 'lrscale' categories
    summarise(count = n(), .groups = 'drop') %>%  # Summarise each group to get counts, and then drop groupings
    mutate(percentage = count / sum(count) * 100)  # Calculate percentage for each group by dividing count by total count and multiplying by 100

lrscale_percentages  # The resulting dataframe
## # A tibble: 4 × 4
##   gndr   lrscale count percentage
##   <chr>  <chr>   <int>      <dbl>
## 1 Female Left      930       23.9
## 2 Female Right     955       24.5
## 3 Male   Left      924       23.7
## 4 Male   Right    1084       27.8

Ans:23.7% of Italian men feel closer to the left party while 27.8% of Italian men feel closer to the right party.

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_  # Set anything that is not 1 or 2 to NA
    ),
    lrscale = case_when(
      lrscale %in% 0:3 ~ "Left",       # Left-wing (0 to 3)
      lrscale %in% 7:10 ~ "Right",     # Right-wing (7 to 10)
      TRUE ~ NA_character_  # Moderate (4, 5, 6) and special codes (77, 88, 99) set to NA 
    )    
  ) 

lrscale_percentages <- sweden_data %>%  # Begin with the dataset 'france_data'
  filter(!is.na(lrscale), !is.na(gndr)) %>%  # Filter out rows where 'lrscale' or 'gender' is NA (missing data)
  group_by(gndr, lrscale) %>%  # Group the data by 'gender' and 'lrscale' categories
  summarise(count = n(), .groups = 'drop') %>%  # Summarise each group to get counts, and then drop groupings
  mutate(percentage = count / sum(count) * 100)  # Calculate percentage for each group by dividing count by total count and multiplying by 100

lrscale_percentages  # The resulting dataframe
## # 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()) +  # Dodged bar chart
  facet_wrap(~ gndr, scales = "fixed") +  # Fixed scales for y-axis across facets
  scale_fill_brewer(palette = "Set1") +  # Distinct colors for Left and Right
  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")  # Legend at the bottom

# Display the ggplot object
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(lrscale), !is.na(geo))  # Removing rows with NA in clsprty or geo

# Calculate conditional probabilities, excluding NAs
cond <- hungary_data %>%
  count(lrscale, geo) %>%
  group_by(geo) %>%
  mutate(prob = n / sum(n))

cond
## # A tibble: 28 × 4
## # Groups:   geo [2]
##    lrscale geo       n   prob
##      <dbl> <chr> <int>  <dbl>
##  1       0 Rural   314 0.0266
##  2       0 Urban   234 0.0483
##  3       1 Rural   233 0.0198
##  4       1 Urban   107 0.0221
##  5       2 Rural   469 0.0398
##  6       2 Urban   215 0.0444
##  7       3 Rural   637 0.0540
##  8       3 Urban   337 0.0696
##  9       4 Rural   632 0.0536
## 10       4 Urban   332 0.0686
## # ℹ 18 more rows

Ans: Given that someone resides in a rural area, the probability of them not feeling close to any particular party is 2.66%