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"
ess <- read.fst("All-ESS-Data.fst")
belgium_data <- read.fst("belgium_data.fst")
serbia_data <- read.fst("serbia_data.fst")
norway_data <- read.fst("norway_data.fst")
portugal_data <- read.fst("portugal_data.fst")
estonia_data <- read.fst("estonia_data.fst")
italy_data <- read.fst("italy_data.fst")
france_data <- read.fst("france_data.fst")
Prompt and question: calculate the average for the variable ‘health’ for the countries of Serbia and Belgium. On average, based on the ESS data, who reports higher levels of subjective health: Serbia and Belgium?
belgium_health <- belgium_data%>%
select(health)
belgium_health$y <- belgium_health$health
table(belgium_health$y)
##
## 1 2 3 4 5 7 8 9
## 4033 9262 3338 674 137 2 3 2
belgium_health$y[belgium_health$y %in% 7:9] <- NA
table(belgium_health$y)
##
## 1 2 3 4 5
## 4033 9262 3338 674 137
mean_belgium <- mean(belgium_health$y, na.rm = TRUE)
cat("Mean of 'y' is:", mean_belgium, "\n")
## Mean of 'y' is: 2.060995
The mean of subjective health in Belgium is 2.060995
serbia_health <- serbia_data%>%
select(health)
serbia_health$y <- serbia_health$health
table(serbia_health$y)
##
## 1 2 3 4 5 8 9
## 620 1051 1332 411 107 3 24
serbia_health$y[serbia_health$y %in% 8:9] <- NA
table(serbia_health$y)
##
## 1 2 3 4 5
## 620 1051 1332 411 107
mean_serbia <- mean(serbia_health$y, na.rm = TRUE)
cat("Mean of 'y' is:", mean_serbia, "\n")
## Mean of 'y' is: 2.526839
The mean of subjective health in Serbia is 2.526839
Therefore Serbians report higher levels of subjective health with 2.526839 compared to 2.060995 reported by Belgians
Prompt and question: what is the most common category selected, for Norwegian respondents, for how often they socially meet with friends or relatives. The variable of interest is: sclmeet.
norway_sclmeet <- norway_data %>%
select(sclmeet)
table(norway_sclmeet$sclmeet)
##
## 1 2 3 4 5 6 7 77 88
## 44 356 746 2569 2119 5764 4458 2 7
norway_sclmeet$sclmeet[norway_sclmeet$sclmeet %in% 77:88] <- NA
table(norway_sclmeet$sclmeet)
##
## 1 2 3 4 5 6 7
## 44 356 746 2569 2119 5764 4458
mode <- norway_sclmeet %>%
mutate(
y_category = case_when(
sclmeet == 1 ~ "Never",
sclmeet == 2 ~ "Less than once a month",
sclmeet == 3 ~ "Once a month",
sclmeet == 4 ~ "Several times a month",
sclmeet == 5 ~ "Once a week",
sclmeet == 6 ~ "Several times a week",
sclmeet == 7 ~ "Every day",
TRUE ~ NA_character_
),
y_category = fct_relevel(factor(y_category),
"Never",
"Less than once a month",
"Once a month",
"Several times a month",
"Once a week",
"Several times a week",
"Every day")
)
table(mode$y_category)
##
## Never Less than once a month Once a month
## 44 356 746
## Several times a month Once a week Several times a week
## 2569 2119 5764
## Every day
## 4458
get_mode <- function(v) {
tbl <- table(v)
mode_vals <- as.character(names(tbl)[tbl == max(tbl)])
return(mode_vals)
}
mode_norway_binge <- get_mode(mode$y_category)
mode_norway_binge
## [1] "Several times a week"
Therefore Norwegian respondents meet with friends or relatives several times a week
Prompt and question: when you use the summary() function for the variable wrclmch (i.e., how worried about climate change) for both the countries of Estonia and Portugal – 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_wrclmch <- ess %>%
filter(cntry == "PT") %>%
select(wrclmch)
table(portugal_wrclmch$wrclmch)
##
## 1 2 3 4 5 6 7 8
## 55 251 1171 1203 380 13 4 31
estonia_wrclmch <- ess %>%
filter(cntry == "EE") %>%
select(wrclmch)
table(estonia_wrclmch$wrclmch)
##
## 1 2 3 4 5 6 7 8
## 343 852 1612 565 125 56 1 7
portugal_wrclmch$wrclmch[portugal_wrclmch$wrclmch %in% 6:8] <- NA
table(portugal_wrclmch$wrclmch)
##
## 1 2 3 4 5
## 55 251 1171 1203 380
estonia_wrclmch$wrclmch[estonia_wrclmch$wrclmch %in% 6:8] <- NA
table(estonia_wrclmch$wrclmch)
##
## 1 2 3 4 5
## 343 852 1612 565 125
summary(portugal_wrclmch)
## wrclmch
## Min. :1.000
## 1st Qu.:3.000
## Median :4.000
## Mean :3.524
## 3rd Qu.:4.000
## Max. :5.000
## NA's :14821
summary(estonia_wrclmch)
## wrclmch
## Min. :1.000
## 1st Qu.:2.000
## Median :3.000
## Mean :2.793
## 3rd Qu.:3.000
## Max. :5.000
## NA's :13359
Therefore two things stand out. The median and the third quantile.It seems that on average, Portuguese people are more likely to be worried about climate change than Estonians evident by the mean. This idea that Portuguese people are more worried about climate change than Estonians is shown in the disproportionate amount of participants in the third quantile in Portugal, compared to Estonia.
Prompt and question: using the variables stfhlth and gndr, answer the following: on average, who is more sastified with health services in Italy, men or women? Explain while referring to the output generated.
table(italy_data$gndr)
##
## 1 2 9
## 4836 5329 13
italy_data$gndr[italy_data$gndr %in% 9] <- NA
table(italy_data$gndr)
##
## 1 2
## 4836 5329
table(italy_data$stfhlth)
##
## 0 1 2 3 4 5 6 7 8 9 10 77 88 99
## 455 279 553 778 958 1470 1718 1869 1363 411 192 24 105 3
italy_data$stfhlth[italy_data$stfhlth %in% 77:99] <- NA
table(italy_data$stfhlth)
##
## 0 1 2 3 4 5 6 7 8 9 10
## 455 279 553 778 958 1470 1718 1869 1363 411 192
italy_data <- italy_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
TRUE ~ as.character(gndr)
)
)
italy_data <- italy_data %>% filter(!is.na(gndr))
italy_data <- italy_data %>% filter(!is.na(stfhlth))
italy_data %>%
group_by(gndr) %>%
summarize(meanstfhlthm = mean(stfhlth, na.rm = TRUE))
## # A tibble: 2 × 2
## gndr meanstfhlthm
## <chr> <dbl>
## 1 Female 5.38
## 2 Male 5.54
Therefore males are more satisfied with health services in Italy evident by the 5.538961, compared to female satisfaction with 5.384791.
Create boxplots, in the same graph, for stfdem and stfgov for the country of France. Provide an appropriate title and labels. Further, tell us: according to ESS data, would we say that the median French person is more satisfied with the democracy or the national government? Explain.
france_data %>%
mutate(stfdem = ifelse(stfdem %in% c(77, 88, 99), NA, stfdem),
stfgov = ifelse(stfgov %in% c(77, 88, 99), NA, stfgov)) %>%
# Reshaping the data
select(stfdem, stfgov) %>%
gather(variable, value, c(stfdem, stfgov)) %>%
# Creating the boxplot
ggplot(aes(x = variable, y = value)) +
geom_boxplot() +
labs(y = "Y-axis", x = "X-axis", title = "Boxplot of stfdem vs. stfgov") +
theme_minimal()
## Warning: Removed 557 rows containing non-finite values (`stat_boxplot()`).
median(france_data$stfdem)
## [1] 5
median(france_data$stfgov)
## [1] 4
france_data %>%
mutate(stfdem = ifelse(stfdem %in% c(77, 88, 99), NA, stfdem),
stfgov = ifelse(stfgov %in% c(77, 88, 99), NA, stfgov)) %>%
select(stfdem, stfgov) %>%
gather(variable, value, c(stfdem, stfgov)) %>%
ggplot(aes(x = variable, y = value)) +
geom_boxplot() +
labs(y = "Satisfaction (0-10)", x = "", title = "Boxplot of Satisfaction With The Ttate of Democracy vs. National Government") +
theme_minimal()
## Warning: Removed 557 rows containing non-finite values (`stat_boxplot()`).
Therefore we would say that the median French person is more satisfied with the democracy, rather than the national government because the median of democracy is 5, whereas the national gtovernment is 4.