# 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"
getwd()
## [1] "C:/Users/dograary/Downloads"
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 and question: calculate the average for the variable ‘happy’ for the country of Norway. On average, based on the ESS data, who reports higher levels of happiness: Norway or Belgium?

Note: we already did it for Belgium. You just need to compare to Norway’s average, making sure to provide the code for both.

belgium_happy <- ess %>% # note: if you work from belgium_data replace "ess" with belgium_data
  filter(cntry == "BE") %>% 
  select(happy)
belgium_happy$y <- belgium_happy$happy

table(belgium_happy$y)
## 
##    0    1    2    3    4    5    6    7    8    9   10   77   88   99 
##   50   27  104  194  234  830  999 3503 6521 3402 1565    3   16    3
# need to remove 77, 88, 99 or else will alter results. See data portal for what they represent (e.g. DK, Refusal, etc.)

# Recode values 77 through 99 to NA
belgium_happy$y[belgium_happy$y %in% 77:99] <- NA

# checking again
table(belgium_happy$y)
## 
##    0    1    2    3    4    5    6    7    8    9   10 
##   50   27  104  194  234  830  999 3503 6521 3402 1565
mean_y <- mean(belgium_happy$y, na.rm = TRUE)
cat("Mean of 'y' is:", mean_y, "\n")
## Mean of 'y' is: 7.737334
norway_happy <- ess %>% # note: if you work from belgium_data replace "ess" with belgium_data
  filter(cntry == "NO") %>% 
  select(happy)
norway_happy$y <- norway_happy$happy

table(norway_happy$y)
## 
##    0    1    2    3    4    5    6    7    8    9   10   77   88 
##   15   29   59  163  238  730  817 2617 5235 3796 2344   12   10
# need to remove 77, 88, 99 or else will alter results. See data portal for what they represent (e.g. DK, Refusal, etc.)

# Recode values 77 through 99 to NA
norway_happy$y[norway_happy$y %in% 77:99] <- NA

# checking again
table(norway_happy$y)
## 
##    0    1    2    3    4    5    6    7    8    9   10 
##   15   29   59  163  238  730  817 2617 5235 3796 2344
mean_y <- mean(norway_happy$y, na.rm = TRUE)
cat("Mean of 'y' is:", mean_y, "\n")
## Mean of 'y' is: 7.975005

The mean avearge of norway is higher then that of Belgium meaning that vpeople in Norway are happier then people in Belgium.

Task 2

Provide code and answer.

Prompt and question: what is the most common category selected, for Irish respondents, for frequency of binge drinking? The variable of interest is: alcbnge.

More info here: https://ess-search.nsd.no/en/variable/0c65116e-7481-4ca6-b1d9-f237db99a694.

Hint: need to convert numeric value entries to categories as specified in the variable information link. We did similar steps for Estonia and the climate change attitude variable.

ireland_ccworried <- ess %>%
  filter(cntry == "IE") %>%
  select(alcbnge)

ireland_ccworried$y <- ireland_ccworried$alcbnge

table(ireland_ccworried$y)
## 
##   1   2   3   4   5   6   7   8 
##  65 650 346 417 239 641  26   6
# Recode values 6 through 8 to NA
ireland_ccworried$y[ireland_ccworried$y %in% 6:8] <- NA
# Converting to categories to get mode as a category instead of a number
df <- ireland_ccworried %>%
  mutate(
    y_category = case_when(
      y == 1 ~ "Daily or almost daily",
      y == 2 ~ "weekly",
      y == 3 ~ "monthly",
      y == 4 ~ "rarely",
      y == 5 ~ "never", 
      TRUE ~ NA_character_
    ),
    y_category = fct_relevel(factor(y_category),  ### here you would put the categories in order you want them to appear or else it will appear alphabetically
                             "Daily or almost daily", 
                             "weekly", 
                             "monthly", 
                             "rarely", 
                             "never")
  )

# To confirm the conversion:
table(df$y_category)
## 
## Daily or almost daily                weekly               monthly 
##                    65                   650                   346 
##                rarely                 never 
##                   417                   239
# Let's determine the mode of our newly created category:

get_mode <- function(v) {
  tbl <- table(v)
  mode_vals <- as.character(names(tbl)[tbl == max(tbl)])
  return(mode_vals)
}

mode_values <- get_mode(df$y_category)
cat("Mode of y category:", paste(mode_values, collapse = ", "), "\n")
## Mode of y category: weekly

The mode was that people in Ireland drink weekley which means that what the most common option chosen.

Task 3

Provide code and answer.

Prompt and question: when you use the summary() function for the variable plnftr (about planning for future or taking every each day as it comes from 0-10) for both the countries of Portugal and Serbia, what do you notice? What stands out as different when you compare the two countries (note: look up the variable information on the ESS website to help with interpretation)? Explain while referring to the output generated.

portugal_ccworried <- ess %>%
  filter(cntry == "PT") %>%
  select(plnftr)
summary(portugal_ccworried)
##      plnftr      
##  Min.   : 0.000  
##  1st Qu.: 3.000  
##  Median : 5.000  
##  Mean   : 6.426  
##  3rd Qu.: 8.000  
##  Max.   :88.000  
##  NA's   :14604
serbia_ccworried <- ess %>%
  filter(cntry == "PT") %>%
  select(plnftr)
summary(serbia_ccworried)
##      plnftr      
##  Min.   : 0.000  
##  1st Qu.: 3.000  
##  Median : 5.000  
##  Mean   : 6.426  
##  3rd Qu.: 8.000  
##  Max.   :88.000  
##  NA's   :14604

The median of serbia was lower then the median of portugal which means people of serbia pefer to plan for things.

Task 4

Provide code and answer.

Prompt and question: using the variables stfdem and gndr, answer the following: on average, who is more dissastified with democracy in Italy, men or women? Explain while referring to the output generated.

Info on variable here: https://ess.sikt.no/en/variable/query/stfdem/page/1

italy_data <- ess %>% 
  filter(cntry == "IT")

# Convert gender and lrscale (representing pol ID self-placement from left to right)
italy_data <- italy_data %>%
  mutate(
    gndr = case_when(
      gndr == 1 ~ "Male",
      gndr == 2 ~ "Female",
      TRUE ~ as.character(gndr)
    ),
    lrscale = ifelse(lrscale %in% c(77, 88), NA, lrscale)  # Convert lrscale values
  )
# Compute average of lrscale by gender
means_by_gender <- italy_data %>%
  group_by(gndr) %>% # here you are "grouping by" your second variable
  summarize(lrscale = mean(lrscale, na.rm = TRUE)) # here you are summarizing your variable of interest

print(means_by_gender)
## # A tibble: 3 × 2
##   gndr   lrscale
##   <chr>    <dbl>
## 1 9         4.6 
## 2 Female    5.09
## 3 Male      5.20

Men on average had a higher rate of satisfaction with democracy then women in France.

Task 5

Provide code and answer.

Prompt: Interpret the boxplot graph of stfedu and stfhlth that we generated already: according to ESS data, would we say that the median French person is more satisfied with the education system or health services? Explain.

Change the boxplot graph: provide the code to change some of the key labels: (1) Change the title to: Boxplot of satisfaction with the state of education vs. health services; (2) Remove the x-axis label; (3) Change the y-axis label to: Satisfaction (0-10).

Hint: copy the boxplot code above and just replace or cut what is asked.

france_data <- ess %>% 
  filter(cntry == "FR")


france_data %>%
  # Setting values to NA
  mutate(stfedu = ifelse(stfedu %in% c(77, 88, 99), NA, stfedu),
         stfhlth = ifelse(stfhlth %in% c(77, 88, 99), NA, stfhlth)) %>%
  # Reshaping the data
  select(stfedu, stfhlth) %>%
  gather(variable, value, c(stfedu, stfhlth)) %>%
  # Creating the boxplot
  ggplot(aes(x = variable, y = value)) +
  geom_boxplot() +
  labs(title = "Boxplot of satisfaction....") +
  theme_minimal()
## Warning: Removed 364 rows containing non-finite values (`stat_boxplot()`).

The median is higher for satisfaction with the health system and lower satisfaction for education system in France.