# List of packages
packages <- c("tidyverse", "fst", "modelsummary", "viridis") # 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
## Warning: package 'viridis' was built under R version 4.3.2
## 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)?

change france to spain

spain_data <- read.fst("spain_data.fst")
## Warning: package 'fstcore' was built under R version 4.3.2
spain_data <- spain_data %>%
  mutate(
    ppltrst = ifelse(ppltrst %in% c(77, 88, 99), NA, ppltrst), # set values 77, 88, and 99 to NA.
  )

Always check your work. One quick way to do so:

table(spain_data$ppltrst) # if there are values that are not supposed to be there (e.g., 77, 88, 99 in this case), then we need to deal with it
## 
##    0    1    2    3    4    5    6    7    8    9   10 
##  932  568 1399 2083 1907 4682 2756 2802 1699  287  254

Next, let’s create a ‘year’ variable from the essround variable. We will use it to visualize.

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

Now, we will calculate the average by year to then visualize:

trust_by_year <- spain_data %>%
  group_by(year) %>%
  summarize(mean_trust = mean(ppltrst, na.rm = TRUE))
trust_by_year
## # A tibble: 10 × 2
##     year mean_trust
##    <dbl>      <dbl>
##  1  2002       4.86
##  2  2004       4.89
##  3  2006       5.12
##  4  2008       4.90
##  5  2010       5.14
##  6  2012       5.13
##  7  2014       4.83
##  8  2016       4.97
##  9  2018       5.09
## 10  2020       4.50
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 Others 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.

Trust in others in spain doesn’t change much in 2002-2022.

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.

read into italy, norway, france
italy_data <- read.fst("italy_data.fst")
norway_data <- read.fst("norway_data.fst")
france_data <- read.fst("france_data.fst")


# Combine data from three countries (France, Norway, Italy) into a single dataset
combined_countries_data <- bind_rows(
  france_data %>% mutate(cntry = "France"),  # Add a new column 'cntry' with the value 'France' to france_data
  norway_data %>% mutate(cntry = "Norway"), # Do the same for norway_data with 'Norway'
  italy_data %>% mutate(cntry = "Italy")    # And for italy_data with 'Italy'
) %>%
  filter(!yrbrn %in% c(7777, 8888)) %>%  # Remove rows where 'yrbrn' (year born) is either 7777 or 8888 (likely missing data codes)
  mutate(
    yrbrn = ifelse(yrbrn > 2005, NA, yrbrn), # Replace 'yrbrn' values greater than 2005 with NA (as they are invalid)
    clsprty = ifelse(clsprty %in% c(7, 8, 9), NA, clsprty), # Replace 'clsprty' values of 7, 8, 9 with NA (considered as invalid or missing)
    clsprty = ifelse(clsprty == 2, 0, clsprty) # Convert 'clsprty' value of 2 to 0 (recoding for analysis purposes)
  )

# Compute proportions for 'clsprty' by 'yrbrn' for each country
clsprty_proportions_compare <- combined_countries_data %>%
  filter(!is.na(yrbrn) & yrbrn >= 1920 & !is.na(clsprty)) %>% # Filter out rows with NA in 'yrbrn' and 'clsprty', and where 'yrbrn' is earlier than 1920
  group_by(yrbrn, cntry) %>% # Group the data by 'yrbrn' (year born) and 'cntry' (country)
  summarise(yes_count = sum(clsprty), total_count = n(), .groups = 'drop') %>% # Summarise data to get count of 'clsprty' and total count per group
  mutate(proportion = yes_count / total_count) # Calculate the proportion of 'clsprty' in each group
# Visualize the data
task2_plot <- ggplot(clsprty_proportions_compare, aes(x = yrbrn, y = proportion, color = cntry)) +  # Initialize ggplot with 'clsprty_proportions' data, setting 'yrbrn' as x-axis, 'proportion' as y-axis, and 'cntry' for color differentiation
  geom_point() +  # Add points to the plot for each data point
  geom_smooth(method = 'loess', se = FALSE) +  # Add a LOESS smoothed line for trend visualization without standard error bands
  labs(
    title = "Proportion Saying 'Yes' to Feeling Close to a Party by Cohort",  # Title of the plot
    x = "Cohort",  # Label for the x-axis
    y = "Proportion",  # Label for the y-axis
    color = "Country"  # Legend title for color coding by country
  ) +
  theme_minimal() +  # Use a minimal theme for a cleaner look
  scale_color_manual(values = c(
    "France" = "#1f77b4",  # Assign a specific color for France
    "Norway" = "#ff7f0e",  # Assign a different color for Norway
    "Italy" = "#2ca02c"    # And another distinct color for Italy
  )) +
  scale_y_continuous(limits = c(0, 1))  # Set the y-axis limits from 0 to 1 as we're dealing with proportions

# Display the plot
task2_plot
## `geom_smooth()` using formula = 'y ~ x'

France,Italy and Norway have a decraeseing level of feeling close to a political party.

Task 3

Provide code and answer.

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

change france to italy, and anythign that says lrscale to clsprty
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
    ),
    clsprty = case_when(
      clsprty %in% 1 ~ "Yes",       # Left-wing (0 to 3)
      clsprty %in% 2 ~ "No",     # Right-wing (7 to 10)
      TRUE ~ NA_character_  # Moderate (4, 5, 6) and special codes (77, 88, 99) set to NA 
    )    
  ) 

Calculations

clsprty_percentages <- italy_data %>%  # Begin with the dataset 'france_data'
  filter(!is.na(clsprty), !is.na(gndr)) %>%  # Filter out rows where 'lrscale' or 'gender' is NA (missing data)
  group_by(gndr, clsprty) %>%  # 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

clsprty_percentages  # The resulting dataframe
## # 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

Male respondents who feel close to a party are 20.5%.

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 
    )    
  ) 

Calculations

lrscale_percentages <- france_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: 26 × 4
##     gndr lrscale count percentage
##    <dbl>   <dbl> <int>      <dbl>
##  1     1       0   457       2.40
##  2     1       1   244       1.28
##  3     1       2   592       3.11
##  4     1       3   909       4.77
##  5     1       4   863       4.53
##  6     1       5  2355      12.4 
##  7     1       6   790       4.15
##  8     1       7   837       4.40
##  9     1       8   700       3.68
## 10     1       9   205       1.08
## # ℹ 16 more rows
# Create a ggplot object for horizontal bar chart with the specified style
lrscale_plot_v2 <- ggplot(lrscale_percentages, 
            aes(x = percentage,  # Use percentage directly
                y = reorder(gndr, -percentage),  # Order bars within each gender
                fill = gndr)) +  # Fill color based on Gender

  # Create horizontal bar chart
  geom_col() +  # Draws the bars using the provided data
  coord_flip() +  # Flip coordinates to make bars horizontal

  # Remove fill color legend
  guides(fill = "none") +  # Removes legend for the fill aesthetic

  # Split the plot based on Political Orientation
  facet_wrap(~ lrscale, nrow = 1) +  # Separate plots for Left/Right

  # Labels and titles for the plot
  labs(x = "Percentage of Respondents",  # X-axis label
       y = NULL,  # Remove Y-axis label
       title = "Political Orientation by Gender",  # Main title
       subtitle = "Comparing the percentage distribution of left vs. right for France (2002-2020)") +  # Subtitle

  # Adjust visual properties of the plot
  theme(plot.title = element_text(size = 16, face = "bold"),  # Format title
        plot.subtitle = element_text(size = 12),  # Format subtitle
        axis.title.y = element_blank(),  # Remove Y-axis title
        legend.position = "bottom")  # Position the legend at the bottom

# Display the ggplot object
lrscale_plot_v2

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(
    gndr = case_when(
      gndr == 1 ~ "Male",
      gndr == 2 ~ "Female",
      TRUE ~ NA_character_  # Set anything that is not 1 or 2 to NA
    ),
    clsprty = case_when(
    clsprty %in% 1 ~ "Yes",       # Left-wing (0 to 3)
      clsprty %in% 2 ~ "No",     # Right-wing (7 to 10)
      TRUE ~ NA_character_  # Moderate (4, 5, 6) and special codes (77, 88, 99) set to NA 
    )    
  ) 
clsprty_percentages <- hungary_data %>%  # Begin with the dataset 'france_data'
  filter(!is.na(clsprty), !is.na(gndr)) %>%  # Filter out rows where 'lrscale' or 'gender' is NA (missing data)
  group_by(gndr, clsprty) %>%  # 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

clsprty_percentages  # The resulting dataframe
## # A tibble: 4 × 4
##   gndr   clsprty count percentage
##   <chr>  <chr>   <int>      <dbl>
## 1 Female No       5071       31.7
## 2 Female Yes      4008       25.0
## 3 Male   No       3608       22.5
## 4 Male   Yes      3334       20.8
# Recode clsprty and geo variables, removing NAs
france_data <- france_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))  # Removing rows with NA in clsprty or geo

In the next step, we will calculate conditional probabilities where:

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

cond
## # A tibble: 26 × 4
## # Groups:   geo [2]
##    lrscale geo       n   prob
##      <dbl> <chr> <int>  <dbl>
##  1       0 Rural   584 0.0446
##  2       0 Urban   360 0.0606
##  3       1 Rural   317 0.0242
##  4       1 Urban   182 0.0306
##  5       2 Rural   810 0.0619
##  6       2 Urban   459 0.0772
##  7       3 Rural  1293 0.0988
##  8       3 Urban   703 0.118 
##  9       4 Rural  1226 0.0937
## 10       4 Urban   611 0.103 
## # ℹ 16 more rows

People are not close to a party if they are rural.