# List of packages
packages <- c("tidyverse", "infer", "fst", "modelsummary", "broom") # 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 --
## v dplyr 1.1.2 v readr 2.1.4
## v forcats 1.0.0 v stringr 1.5.0
## v ggplot2 3.4.3 v tibble 3.2.1
## v lubridate 1.9.2 v tidyr 1.3.0
## v purrr 1.0.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
## i Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors## [[1]]
## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [13] "grDevices" "utils" "datasets" "methods" "base"
##
## [[2]]
## [1] "infer" "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [7] "readr" "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [13] "graphics" "grDevices" "utils" "datasets" "methods" "base"
##
## [[3]]
## [1] "fst" "infer" "lubridate" "forcats" "stringr" "dplyr"
## [7] "purrr" "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [13] "stats" "graphics" "grDevices" "utils" "datasets" "methods"
## [19] "base"
##
## [[4]]
## [1] "modelsummary" "fst" "infer" "lubridate" "forcats"
## [6] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [11] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [16] "grDevices" "utils" "datasets" "methods" "base"
##
## [[5]]
## [1] "broom" "modelsummary" "fst" "infer" "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")Filtering and recoding:
belgium_data <- ess %>%
filter(cntry == "BE") %>%
mutate(trstep = ifelse(trstep %in% c(77, 88, 99), NA, trstep), # Filtering 'Trust in the European Parliament' in Belgium.
)unique(belgium_data$trstep)## [1] 0 7 8 5 6 NA 4 9 3 1 10 2belgium_data <- belgium_data %>% filter(!is.na(trstep))belgium_data <- belgium_data %>%
mutate(wrkprty = case_when(
wrkprty == 1 ~ "Yes",
wrkprty == 2 ~ "No",
wrkprty %in% c(7, 8, 9) ~ NA_character_,
TRUE ~ as.character(wrkprty)
))
table(belgium_data$wrkprty)##
## No Yes
## 14871 727Producing a linear regression model:
model_m1 <- lm(trstep ~ wrkprty, data = belgium_data)Extracting coefficients and intercept:
coefficients <- coef(model_m1)
print(coefficients)## (Intercept) wrkprtyYes
## 4.9405554 0.4308338Interpretation:
An intercept of 4.94 indicates that when looking at respondents who have NOT worked in a political party, the expected value of their trust in the European Parliament is approximately 4.94.
A coefficient of 0.43 indicates that when looking at respondents who HAVE worked in a political party, there is an increase of approximately 0.43 in the predicted value of their trust in the European Parliament, compared to respondents who have not worked in a political party.
Filtering and recoding:
bulgaria_data <- ess %>%
filter(cntry == "BG") %>%
mutate(stfdem = ifelse(stfdem %in% c(77, 88, 99), NA, stfdem), # Filtering 'Satisfaction with Democracy' in Bulgaria
)unique(bulgaria_data$stfdem)## [1] 0 1 NA 2 3 5 4 6 8 7 10 9bulgaria_data <- bulgaria_data %>% filter(!is.na(stfdem))bulgaria_data <- bulgaria_data %>%
mutate(
native = recode(brncntr,
`1` = "Yes",
`2` = "No",
`7` = NA_character_,
`8` = NA_character_,
`9` = NA_character_)
)
table(bulgaria_data$native)##
## No Yes
## 97 12239Producing a linear regression model:
model_m2 <- lm(stfdem ~ native, data = bulgaria_data)Extracting coefficient and intercept:
coefficients <- coef(model_m2)
print(coefficients)## (Intercept) nativeYes
## 2.8041237 0.1189909Producing a summary model output:
tidy(model_m2)## # A tibble: 2 x 5
## term estimate std.error statistic p.value
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 (Intercept) 2.80 0.226 12.4 5.30e-35
## 2 nativeYes 0.119 0.227 0.523 6.01e- 1Interpretation:
The expected average of satisfaction with democracy for respondents who were NOT born in Bulgaria is 2.8, as indicated by an intercept value of 2.8.
Filtering and recoding:
germany_data <- ess %>%
filter(cntry == "DE") %>%
mutate(trstep = ifelse(trstep %in% c(77, 88, 99), NA, trstep), # Filtering 'Trust in the European Parliament' in Germany as my outcome variable of interest.
)unique(germany_data$trstep)## [1] 7 NA 5 10 6 8 3 2 9 4 0 1germany_data <- germany_data %>% filter(!is.na(trstep))germany_data <- germany_data %>%
mutate(
minority = case_when(
blgetmg %in% c(7, 8, 9) ~ NA_character_,
blgetmg == 1 ~ "Ethnic Minority",
blgetmg == 2 ~ "Not Ethnic Minority",
TRUE ~ as.character(blgetmg)
))
table(germany_data$minority)##
## Ethnic Minority Not Ethnic Minority
## 1095 22820Producing a linear regression model:
model_m3 <- lm(trstep ~ minority, data = germany_data)Extracting coefficents and intercept:
coefficients <- coef(model_m3)
print(coefficients)## (Intercept) minorityNot Ethnic Minority
## 4.8173516 -0.6333025Producing an equation output with equatiomatic:
remotes::install_github("datalorax/equatiomatic")## Skipping install of 'equatiomatic' from a github remote, the SHA1 (29ff168f) has not changed since last install.
## Use `force = TRUE` to force installationequatiomatic::extract_eq(model_m3, use_coefs = TRUE)\[ \operatorname{\widehat{trstep}} = 4.82 - 0.63(\operatorname{minority}_{\operatorname{Not\ Ethnic\ Minority}}) \] Interpretation:
This regression equation indicates that the approximate predicted value of respondents’ trust in the European Parliament, given that they are NOT an ethnic minority, is about 4.82 - 0.63, or 4.19. Looking at respondents who ARE an ethnic minority, the average predicted value of trstep is 4.82.