Tutorial 7 (SOC222)
Setting up environment
# List of packages
packages <- c("tidyverse", "infer", "fst", "modelsummary", "effects", "survey", "interactions") # 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 1.1.4 ✔ readr 2.1.4
## ✔ 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: carData
##
## lattice theme set by effectsTheme()
## See ?effectsTheme for details.
##
## Loading required package: grid
##
## Loading required package: Matrix
##
##
## Attaching package: 'Matrix'
##
##
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack
##
##
## Loading required package: survival
##
##
## Attaching package: 'survey'
##
##
## The following object is masked from 'package:graphics':
##
## dotchart## [[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] "effects" "carData" "modelsummary" "fst" "infer"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[6]]
## [1] "survey" "survival" "Matrix" "grid" "effects"
## [6] "carData" "modelsummary" "fst" "infer" "lubridate"
## [11] "forcats" "stringr" "dplyr" "purrr" "readr"
## [16] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [21] "graphics" "grDevices" "utils" "datasets" "methods"
## [26] "base"
##
## [[7]]
## [1] "interactions" "survey" "survival" "Matrix" "grid"
## [6] "effects" "carData" "modelsummary" "fst" "infer"
## [11] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [16] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [21] "stats" "graphics" "grDevices" "utils" "datasets"
## [26] "methods" "base"Task 1
Graph the histogram distribution using the populist scale (as we did in the tutorial) for the country of Sweden. What do you note?
sweden_data <- read.fst("sweden_data.fst")
sweden_data$trstplt <- ifelse(sweden_data$trstplt > 10, NA, sweden_data$trstplt)
sweden_data$trstprl <- ifelse(sweden_data$trstprl > 10, NA, sweden_data$trstprl)
sweden_data$trstprt <- ifelse(sweden_data$trstprt > 10, NA, sweden_data$trstprt)
sweden_data$trust <- scales::rescale(sweden_data$trstplt + sweden_data$trstprl + sweden_data$trstprt, na.rm = TRUE, to = c(0, 100))
sweden_data$populist <- scales::rescale(sweden_data$trust, na.rm = TRUE, to=c(100,0))
ggplot(sweden_data, aes(x = populist)) +
geom_histogram(bins = 30, fill = "blue", color = "black") +
theme_minimal() +
labs(title = "Distribution of Populist Scale for Sweden",
x = "Populist Scale",
y = "Count")## Warning: Removed 2503 rows containing non-finite values (`stat_bin()`).
##The Populist Scale for Norway shows that the highest count is between
2000 to 2010 people who support populism which the histogram shows as 40
people.
Task 2
sweden_data <- read.fst("sweden_data.fst")# Setting values greater than 10 to NA
sweden_data$trstplt <- ifelse(sweden_data$trstplt > 10, NA, sweden_data$trstplt)
sweden_data$trstprl <- ifelse(sweden_data$trstprl > 10, NA, sweden_data$trstprl)
sweden_data$trstprt <- ifelse(sweden_data$trstprt > 10, NA, sweden_data$trstprt)# Creating and rescaling the trust variable
sweden_data$trust <- scales::rescale(sweden_data$trstplt + sweden_data$trstprl + sweden_data$trstprt, na.rm = TRUE, to = c(0, 100))
sweden_data$populist <- scales::rescale(sweden_data$trust, na.rm = TRUE, to=c(100,0))
ggplot(sweden_data, aes(x = populist)) +
geom_histogram(bins = 30, fill = "blue", color = "black") +
theme_minimal() +
labs(title = "Distribution of Populist Scale for Sweden",
x = "Populist Scale",
y = "Educational Attainment")## Warning: Removed 2503 rows containing non-finite values (`stat_bin()`).
sweden_data <- sweden_data %>%
mutate(
ID = case_when(
lrscale %in% 0:4 ~ "Left", # This time: Values 0 to 3 in 'lrscale' are categorized as "Left"
lrscale %in% 6:10 ~ "Right", # This time: Values 6 to 10 in 'lrscale' are categorized as "Right"
lrscale %in% c(77, 88, 99) ~ NA_character_, # Values 77, 88, 99 in 'lrscale' are set as NA
TRUE ~ NA_character_ # Any other values not explicitly matched above
)
)
table(sweden_data$ID)##
## Left Right
## 6188 7406sweden_pop_model <- lm(populist ~ ID, data = sweden_data)coefficients_sweden <- coef(sweden_pop_model)
print(coefficients_sweden)## (Intercept) IDRight
## 48.3188406 -0.7149274#In Sweden there is a score of 48 in terms of people who are in the left group and -0.7 in terms of people who are in the right group. This shows the populist attitudes in Sweden.
summary(sweden_pop_model)##
## Call:
## lm(formula = populist ~ ID, data = sweden_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -48.319 -14.271 -1.652 12.396 52.396
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 48.3188 0.2647 182.562 <2e-16 ***
## IDRight -0.7149 0.3555 -2.011 0.0444 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 19.25 on 11864 degrees of freedom
## (6350 observations deleted due to missingness)
## Multiple R-squared: 0.0003407, Adjusted R-squared: 0.0002565
## F-statistic: 4.044 on 1 and 11864 DF, p-value: 0.04436#P Value of Sweden is 0.04436 which means 0.04436 in the Swedish population is the mean in terms of populsit attitudes. There is no - meaning it did not decrease.
Task 3
italy_data <-read.fst ("italy_data.fst")
## Creates an authoritarian values scale based on human modules items (can also do libertarian value scale)
italy_data <- italy_data %>%
mutate(behave = ipbhprp,
secure = impsafe,
safety = ipstrgv,
tradition = imptrad,
rules = ipfrule) %>%
mutate(across(c("behave", "secure", "safety", "tradition", "rules"),
~ na_if(.x, 7) %>% na_if(8) %>% na_if(9))) %>%
mutate(across(c("behave", "secure", "safety", "tradition", "rules"), ~ 7 - .x ))
italy_data$auth <- scales::rescale(italy_data$behave +
italy_data$secure +
italy_data$safety +
italy_data$tradition +
italy_data$rules, to=c(0,100), na.rm=TRUE)
italy_data <- italy_data %>% filter(!is.na(auth))
table(italy_data$secure)##
## 1 2 3 4 5 6
## 54 139 626 1856 2876 2881italy_data$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
italy_data$year[italy_data$essround == i] <- replacements[i]
}
auth_avg <- italy_data %>%
group_by(year) %>%
summarize(auth_avg = mean(auth, na.rm = TRUE))
plot_auth <- ggplot(auth_avg, aes(x = year, y = auth_avg)) +
geom_point(aes(color = auth_avg), alpha = 1.0) +
geom_line(aes(group = 1), color = "blue", linetype = "dashed") +
labs(title = "Authoritarian Scale Average by Year (Portugal)",
x = "Survey Year",
y = "Authoritarian Scale Average") +
theme_minimal() +
theme(legend.position = "none") +
scale_y_continuous(limits = c(0, 100))
print(plot_auth)
##Based on this data, the Authoritarian Scale from 2012 to 2020 remains
consistent with an average at approximately 75. The average slightly
decreases from 2010 to 2016 as the average in 2016 droped to an average
of 70, differing from the initial average of 75.
Task 4
italy_data <- read.fst("italy_data.fst")italy_data$trstplt <- ifelse(italy_data$trstplt > 10, NA, italy_data$trstplt)
italy_data$trstprl <- ifelse(italy_data$trstprl > 10, NA, italy_data$trstprl)
italy_data$trstprt <- ifelse(italy_data$trstprt > 10, NA, italy_data$trstprt)italy_data$trust <- scales::rescale(italy_data$trstplt + italy_data$trstprl + italy_data$trstprt, na.rm = TRUE, to = c(0, 100))
italy_data$populist <- scales::rescale(italy_data$trust, na.rm = TRUE, to=c(100,0))
ggplot(italy_data, aes(x = populist)) +
geom_histogram(bins = 30, fill = "blue", color = "black") +
theme_minimal() +
labs(title = "Distribution of Populist Scale for Italy",
x = "Populist Scale",
y = "Educational Attainment")## Warning: Removed 1493 rows containing non-finite values (`stat_bin()`).
italy_data <- italy_data %>%
mutate(
ID = case_when(
lrscale %in% 0:4 ~ "Left",
lrscale %in% 6:10 ~ "Right",
lrscale %in% c(77, 88, 99) ~ NA_character_,
TRUE ~ NA_character_
)
)
table(italy_data$ID)##
## Left Right
## 2662 2834italy_pop_model <- lm(populist ~ ID, data = italy_data)coef_italy <- coef(italy_pop_model)
print(coef_italy)## (Intercept) IDRight
## 64.899080 2.999471summary(italy_pop_model)##
## Call:
## lm(formula = populist ~ ID, data = italy_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -67.899 -17.899 -1.232 18.434 35.101
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 64.8991 0.4568 142.087 <2e-16 ***
## IDRight 2.9995 0.6303 4.759 2e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 21.65 on 4728 degrees of freedom
## (5448 observations deleted due to missingness)
## Multiple R-squared: 0.004767, Adjusted R-squared: 0.004557
## F-statistic: 22.65 on 1 and 4728 DF, p-value: 2.005e-06#The R Square is -0.0001472, meaning there has been a decrease in this data representing Italy that represents authoritarian values in Italy.
Task 5
greece_data <- read.fst("greece_data.fst")According to this data, citizens of Greece who are a part of genBaby Boomers have the highest confidence intervals, of -1 tied with those with a education of a BA and higher. GenMillenials have the lowest confidence intervals of -4 and the rest remain in the middle.