# List of packages
packages <- c("tidyverse", "infer", "fst", "modelsummary", "effects", "survey", "interactions","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)
## Warning: package 'readr' was built under R version 4.2.3
## Warning: package 'dplyr' was built under R version 4.2.3
## Warning: package 'stringr' was built under R version 4.2.3
## ── 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
## Warning: package 'infer' was built under R version 4.2.3
## Loading required package: carData
## lattice theme set by effectsTheme()
## See ?effectsTheme for details.
## Warning: package 'survey' was built under R version 4.2.3
## 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
##
## Registered S3 methods overwritten by 'broom':
## method from
## tidy.glht jtools
## tidy.summary.glht jtools
## [[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"
##
## [[8]]
## [1] "broom" "interactions" "survey" "survival" "Matrix"
## [6] "grid" "effects" "carData" "modelsummary" "fst"
## [11] "infer" "lubridate" "forcats" "stringr" "dplyr"
## [16] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [21] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [26] "datasets" "methods" "base"
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")
## Warning: package 'fstcore' was built under R version 4.2.3
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$trust, na.rm = TRUE, to=c(100,0))
ggplot(sweden_data, aes(x = populist)) +
geom_histogram(bins = 30, fill = "green", color = "black") +
theme_minimal() +
labs(title = "Distribution of Populist Scale for Sweden",
x = "Populist Scale",
y = "Count")
## Warning: Removed 2503 rows containing non-finite values (`stat_bin()`).
The histogram is slightly right skewed with the high levels from 0-50 on the populist scale and low levels 50 onwards on the populist scale.Furthermore there is a clear mode less than 50 as well on the populist scale.
Run a linear regression with populist attitudes as the outcome, educational attainment (recoded as a binary “BA or more” and “No BA”), and using the Swedish data. Print the intercept and coefficients only and interpret. Then do a tidy model table displaying the p-value (with digits = 3) and interpret.
sweden_data <- sweden_data %>%
mutate(
educ.ba = case_when(
essround < 5 & edulvla == 5 ~ "BA or more",
essround >= 5 & edulvlb > 600 ~ "BA or more",
TRUE ~ "No BA"
),
edulvla = ifelse(edulvla %in% c(77, 88, 99), NA_integer_, edulvla),
edulvlb = ifelse(edulvlb %in% c(5555, 7777, 8888), NA_integer_, edulvlb),
educ.ba = factor(educ.ba, levels = c("No BA", "BA or more"))
)
table(sweden_data$educ.ba)
##
## No BA BA or more
## 13477 4739
sweden_pop_model <- lm(populist ~ educ.ba, data = sweden_data)
coefficients_sweden <- coef(sweden_pop_model)
print(coefficients_sweden)
## (Intercept) educ.baBA or more
## 51.358680 -7.868121
tidy(sweden_pop_model) |>
knitr::kable(digits = 3)
| term | estimate | std.error | statistic | p.value |
|---|---|---|---|---|
| (Intercept) | 51.359 | 0.181 | 283.363 | 0 |
| educ.baBA or more | -7.868 | 0.350 | -22.494 | 0 |
A clear association between populist attitudes and educational attainment do exist
Now using the Italian dataset and the authoritarian values scale (as we did in the tutorial), graph the average by survey year. Interpret.
library(dplyr)
library(ggplot2)
italy_data <- read.fst("italy_data.fst")
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$secure)
##
## 1 2 3 4 5 6
## 54 139 626 1856 2876 2881
table(italy_data$auth)
##
## 0 12 16 20 24 28 32 36 40 44 48 52 56 60 64 68 72 76 80 84
## 7 4 4 9 13 20 27 57 113 155 163 323 367 596 647 789 823 897 992 733
## 88 92 96 100
## 632 465 299 297
italy_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$essround == i] <- replacements[i]
}
auth_avg <- italy_data %>%
group_by(year) %>%
summarize(auth_avg = mean(auth, na.rm = TRUE))
plot_auth <- ggplot(auth_avg, aes(x = year, y = auth_avg)) +
geom_point(aes(color = auth_avg), alpha = 1.0) +
geom_line(aes(group = 1), color = "black", linetype = "dashed") +
labs(title = "Authoritarian Scale Average by Year (Portugal)",
x = "Survey Year",
y = "Authoritarian Scale Average") +
theme_minimal() +
theme(legend.position = "none") +
scale_y_continuous(limits = c(0, 100))
print(plot_auth)
The average reduces to 73 in the year of 2016 before slightly rising
till 74 between the years 2018-2020.
Now run a linear regression model, using the modelsummary package, with authoritarian values as the outcome, and generations as the predictor/potential explanatory variable, and using the Italian data again. Rename the coefficients using the coef_rename function. Interpret the coefficients, whether they are statistically significant, and the adjusted R-squared.
model_data <- italy_data %>%
mutate(
cohort = ifelse(yrbrn < 1930 | yrbrn > 2000, NA, yrbrn),
gen = case_when(
yrbrn %in% 1900:1945 ~ "1",
yrbrn %in% 1946:1964 ~ "2",
yrbrn %in% 1965:1979 ~ "3",
yrbrn %in% 1980:1996 ~ "4",
TRUE ~ as.character(cohort)
),
gen = factor(gen,
levels = c("1", "2", "3", "4"),
labels = c("Interwar", "Baby Boomers", "Gen X", "Millennials"))
)
table(model_data$gen)
##
## Interwar Baby Boomers Gen X Millennials
## 1026 2580 2214 1811
model <- lm(auth ~ gen, data = model_data)
modelsummary(
list(model),coef_rename = c("genBaby Boomers" = "Baby Boomers", "genGen X" = "Gen X", "genMillennials" = "Millennials"))
| (1) | |
|---|---|
| (Intercept) | 75.345 |
| (0.467) | |
| Baby Boomers | −1.125 |
| (0.552) | |
| Gen X | −2.080 |
| (0.564) | |
| Millennials | −3.592 |
| (0.584) | |
| Num.Obs. | 7631 |
| R2 | 0.006 |
| R2 Adj. | 0.006 |
| AIC | 62934.0 |
| BIC | 62968.7 |
| Log.Lik. | −31462.009 |
| RMSE | 14.94 |
Here it i illustrated through the intercept that the avg. expected authoritarian score will ve 75.3, when all other predictable values are zero.
the co-efficient of Baby Boomers is -1.1, showcasing the authoritarian scale score being 1.1. With P almost equal to 0.05, it is not statistically significant since it is denoted by one asterisk
the co-efficient of Gen X is -2. 1, showcasing the authoritarian scale score -2.1. With P being lesser than 0.05, it is statistically significant since it is denoted by three asterisks
the co-efficient of Millenials is -3.6, showcasing that authoritarian scale score 3.6. With P being lesser than 0.05, it is statistically significant since it is denoted by three asterisks
Now visualize, using the modelplot() function from the modelsummary package, coefficient estimates and 95% confidence intervals for the following three models:
Model 1 = populist attitudes scale as the outcome; left/right as the single predictor (omitting moderates as we did in the tutorial), and using data for Greece.
Model 2 = populist attitudes scale as the outcome; gender as the single predictor, and using data for Greece.
Model 3 = populist attitudes scale as the outcome; generations as the single predictor (using the four generational category recode we did in the tutorial), and using data for Greece. Interpret.
greece_data <- read.fst("greece_data.fst")
greece_data$trstplt <- ifelse(greece_data$trstplt > 10, NA, greece_data$trstplt)
greece_data$trstprl <- ifelse(greece_data$trstprl > 10, NA, greece_data$trstprl)
greece_data$trstprt <- ifelse(greece_data$trstprt > 10, NA, greece_data$trstprt)
greece_data$trust <- scales::rescale(greece_data$trstplt + greece_data$trstprl + greece_data$trstprt, na.rm = TRUE, to = c(0, 100))
greece_data$populist <- scales::rescale(greece_data$trust, na.rm = TRUE, to=c(100,0))
model_data <- greece_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
gndr == 9 ~ NA_character_,
TRUE ~ as.character(gndr)
),
age = ifelse(agea == 999, NA, agea),
cohort = ifelse(yrbrn < 1930 | yrbrn > 2000, NA, yrbrn),
gen = case_when(
yrbrn %in% 1900:1945 ~ "1",
yrbrn %in% 1946:1964 ~ "2",
yrbrn %in% 1965:1979 ~ "3",
yrbrn %in% 1980:1996 ~ "4",
TRUE ~ as.character(cohort)
),
ID = case_when(
lrscale %in% 0:3 ~ "Left", # Values 0 to 3 in 'lrscale' are categorized as "Left"
lrscale %in% 7:10 ~ "Right", # Values 7 to 10 in 'lrscale' are categorized as "Right"
#lrscale %in% 4:6 ~ "Moderate", # Values 4 to 6 in 'lrscale' are categorized as "Moderate"
lrscale %in% c(4,5,6,77, 88, 99) ~ NA_character_ # Values 77, 88, 99 in 'lrscale' are set as NA
),
gen = factor(gen,
levels = c("1", "2", "3", "4"),
labels = c("Interwar", "Baby Boomers", "Gen X", "Millennials"))
)
models <- list(
"Model 1" = lm(populist ~ ID, data = model_data),
"Model 2" = lm(populist ~ gndr, data = model_data),
"Model 3" = lm(populist ~ gen, data = model_data))
modelsummary(models, fmt = 1,
estimate = c("{estimate} ({std.error}){stars}",
"{estimate} ({std.error}){stars}",
"{estimate} ({std.error}){stars}"),
statistic = NULL)
| Model 1 | Model 2 | Model 3 | |
|---|---|---|---|
| (Intercept) | 72.4 (0.6)*** | 70.0 (0.3)*** | 65.8 (0.5)*** |
| IDRight | −10.5 (0.8)*** | ||
| gndrMale | −1.0 (0.5)* | ||
| genBaby Boomers | 3.5 (0.7)*** | ||
| genGen X | 5.6 (0.7)*** | ||
| genMillennials | 5.8 (0.7)*** | ||
| Num.Obs. | 3480 | 9823 | 9562 |
| R2 | 0.048 | 0.000 | 0.009 |
| R2 Adj. | 0.048 | 0.000 | 0.009 |
| AIC | 31648.1 | 88873.2 | 86473.9 |
| BIC | 31666.6 | 88894.8 | 86509.7 |
| Log.Lik. | −15821.063 | −44433.590 | −43231.944 |
| RMSE | 22.81 | 22.30 | 22.25 |
models <- list(
"Model 1" = lm(populist ~ ID, data = model_data),
"Model 2" = lm(populist ~ gndr, data = model_data),
"Model 3" = lm(populist ~ gen, data = model_data))
modelsummary(models, fmt = 1,
estimate = c("{estimate} ({std.error}){stars}",
"{estimate} ({std.error}){stars}",
"{estimate} ({std.error}){stars}"),
statistic = NULL)
| Model 1 | Model 2 | Model 3 | |
|---|---|---|---|
| (Intercept) | 72.4 (0.6)*** | 70.0 (0.3)*** | 65.8 (0.5)*** |
| IDRight | −10.5 (0.8)*** | ||
| gndrMale | −1.0 (0.5)* | ||
| genBaby Boomers | 3.5 (0.7)*** | ||
| genGen X | 5.6 (0.7)*** | ||
| genMillennials | 5.8 (0.7)*** | ||
| Num.Obs. | 3480 | 9823 | 9562 |
| R2 | 0.048 | 0.000 | 0.009 |
| R2 Adj. | 0.048 | 0.000 | 0.009 |
| AIC | 31648.1 | 88873.2 | 86473.9 |
| BIC | 31666.6 | 88894.8 | 86509.7 |
| Log.Lik. | −15821.063 | −44433.590 | −43231.944 |
| RMSE | 22.81 | 22.30 | 22.25 |
modelplot(models, coef_omit = 'Interc') +
labs( title = 'Coefficients estimtates within the 95% Confidence Interval')
the Baby Boomer cohort is likely to score 3.5 higher when compared to our reference category since the co-efficient of this group is 3.5. In regards to Gen Z, a great difference from the reference category for the authoritarian score is visible, since the co-efficient of this group is 5.6. Finally for Millenials since the co-efficient is 5.8 the greatest difference can be noted when compared to the reference category on the authoritarian scale score.
Since the asterisk is three as illustrates that P is less that 0.005 this is statically significant.the variable gen only illustrates 0.9% of variance in the data according to the adjusted R value