Wilson_Marina_Homework_5
2024-03-21
# List of packages
packages <- c("tidyverse", "infer", "fst", "broom", "modelsummary", "effects", "survey", "MASS", "aod", "interactions", "kableExtra", "flextable", "scales") # 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## Warning: package 'infer' was built under R version 4.3.3## Warning: package 'effects' was built under R version 4.3.3## Loading required package: carData## Warning: package 'carData' was built under R version 4.3.3## lattice theme set by effectsTheme()
## See ?effectsTheme for details.## Warning: package 'survey' was built under R version 4.3.3## 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
##
##
## Attaching package: 'MASS'
##
## The following object is masked from 'package:dplyr':
##
## select## Warning: package 'aod' was built under R version 4.3.3##
## Attaching package: 'aod'
##
## The following object is masked from 'package:survival':
##
## rats## Warning: package 'interactions' was built under R version 4.3.3##
## Attaching package: 'kableExtra'
##
## The following object is masked from 'package:dplyr':
##
## group_rows
##
##
## Attaching package: 'flextable'
##
## The following objects are masked from 'package:kableExtra':
##
## as_image, footnote
##
## The following object is masked from 'package:purrr':
##
## compose
##
##
## Attaching package: 'scales'
##
## The following object is masked from 'package:purrr':
##
## discard
##
## The following object is masked from 'package:readr':
##
## col_factor## [[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] "broom" "fst" "infer" "lubridate" "forcats" "stringr"
## [7] "dplyr" "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [13] "tidyverse" "stats" "graphics" "grDevices" "utils" "datasets"
## [19] "methods" "base"
##
## [[5]]
## [1] "modelsummary" "broom" "fst" "infer" "lubridate"
## [6] "forcats" "stringr" "dplyr" "purrr" "readr"
## [11] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [16] "graphics" "grDevices" "utils" "datasets" "methods"
## [21] "base"
##
## [[6]]
## [1] "effects" "carData" "modelsummary" "broom" "fst"
## [6] "infer" "lubridate" "forcats" "stringr" "dplyr"
## [11] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [16] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [21] "datasets" "methods" "base"
##
## [[7]]
## [1] "survey" "survival" "Matrix" "grid" "effects"
## [6] "carData" "modelsummary" "broom" "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] "MASS" "survey" "survival" "Matrix" "grid"
## [6] "effects" "carData" "modelsummary" "broom" "fst"
## [11] "infer" "lubridate" "forcats" "stringr" "dplyr"
## [16] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [21] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [26] "datasets" "methods" "base"
##
## [[9]]
## [1] "aod" "MASS" "survey" "survival" "Matrix"
## [6] "grid" "effects" "carData" "modelsummary" "broom"
## [11] "fst" "infer" "lubridate" "forcats" "stringr"
## [16] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [21] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [26] "utils" "datasets" "methods" "base"
##
## [[10]]
## [1] "interactions" "aod" "MASS" "survey" "survival"
## [6] "Matrix" "grid" "effects" "carData" "modelsummary"
## [11] "broom" "fst" "infer" "lubridate" "forcats"
## [16] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [21] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [26] "grDevices" "utils" "datasets" "methods" "base"
##
## [[11]]
## [1] "kableExtra" "interactions" "aod" "MASS" "survey"
## [6] "survival" "Matrix" "grid" "effects" "carData"
## [11] "modelsummary" "broom" "fst" "infer" "lubridate"
## [16] "forcats" "stringr" "dplyr" "purrr" "readr"
## [21] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [26] "graphics" "grDevices" "utils" "datasets" "methods"
## [31] "base"
##
## [[12]]
## [1] "flextable" "kableExtra" "interactions" "aod" "MASS"
## [6] "survey" "survival" "Matrix" "grid" "effects"
## [11] "carData" "modelsummary" "broom" "fst" "infer"
## [16] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [21] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [26] "stats" "graphics" "grDevices" "utils" "datasets"
## [31] "methods" "base"
##
## [[13]]
## [1] "scales" "flextable" "kableExtra" "interactions" "aod"
## [6] "MASS" "survey" "survival" "Matrix" "grid"
## [11] "effects" "carData" "modelsummary" "broom" "fst"
## [16] "infer" "lubridate" "forcats" "stringr" "dplyr"
## [21] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [26] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [31] "datasets" "methods" "base"Homework 5:
Task 1
Use data for Germany and the variable coding for model3 and model4 from the tutorial (i.e., both for the cleaning & recode, as well as the linear model formulas). Do a modelsummary table displaying both model outputs. Interpret the coefficients for the MLR without the interaction (i.e., the first displayed model), and interpret model fit metrics for both models.
germany_data <- read_fst("germany_data.fst")
df <- germany_datadf$weight <- df$dweight * df$pweight
survey_design <- svydesign(ids = ~1, data = df, weights = ~weight)df <- df %>%
mutate(behave = ipbhprp,
secure = impsafe,
safety = ipstrgv,
tradition = imptrad,
rules = ipfrule) %>%
mutate(across(c("behave", "secure", "safety", "tradition", "rules"),
~ na_if(.x, 7) %>% na_if(8) %>% na_if(9))) %>%
# Apply the reverse coding
mutate(across(c("behave", "secure", "safety", "tradition", "rules"), ~ 7 - .x ))
# Now you can calculate 'schwartzauth' after the NA recoding
df$auth <- scales::rescale(df$behave +
df$secure +
df$safety +
df$tradition +
df$rules, to=c(0,100), na.rm=TRUE)
df <- df %>% filter(!is.na(auth))df <- df %>%
mutate(
polID = case_when(
lrscale %in% 0:3 ~ "Left",
lrscale %in% 7:10 ~ "Right",
lrscale %in% 4:6 ~ "Moderate",
lrscale %in% c(77, 88, 99) ~ NA_character_
),
religious = case_when(
rlgdgr %in% c(77, 88, 99) ~ NA_real_,
TRUE ~ rlgdgr
)
)model3 <- lm(auth ~ polID + religious, data = df, weights = weight)
model4 <- lm(auth ~ polID + religious + polID*religious, data = df, weights = weight)
modelsummary(
list(model3, model4),
fmt = 1,
estimate = c( "{estimate} ({std.error}){stars}",
"{estimate} ({std.error}){stars}"),
statistic = NULL)| (1) | (2) | |
|---|---|---|
| (Intercept) | 55.3 (0.3)*** | 56.4 (0.3)*** |
| polIDModerate | 4.6 (0.3)*** | 3.4 (0.4)*** |
| polIDRight | 7.7 (0.4)*** | 4.2 (0.7)*** |
| religious | 0.9 (0.0)*** | 0.6 (0.1)*** |
| polIDModerate × religious | 0.3 (0.1)*** | |
| polIDRight × religious | 0.8 (0.1)*** | |
| Num.Obs. | 23373 | 23373 |
| R2 | 0.048 | 0.050 |
| R2 Adj. | 0.048 | 0.050 |
| AIC | 200594.1 | 200558.6 |
| BIC | 200634.4 | 200615.0 |
| Log.Lik. | −100292.049 | −100272.298 |
| RMSE | 17.27 | 17.24 |
## Interpreting Coefficients (No Interaction): A coefficient of 4.6 for polIDModerate indicates that, comparing individuals with the same religiousness, the average outcome for individuals identifying as politically moderate are 4.6 units higher compared to the reference category (left-wing individuals). A coefficient of 7.7 for polIDRight indicates that, comparing individuals with the same religiousness, the average outcome for individuals identifying as politically right is 7.7 units higher than the reference category. Finally, for the "religious" predictor, a coefficient of 0.9 means that for every one-unit increase in religiousness, there is an associated expected average increase of 0.9 units on the authoritarian values scale, assuming we are comparing people with the same ideological categorization. All three coefficients have ***, indicating a p < 0.001. There is less than a 0.1% probability that the observed result is due to chance, so we do not reject the null. ## Interpreting Model Fit Metrics: An adjusted R-Squared value of 0.048 for the first model means that political ideology (left/right/moderate) among individuals with the same religiousness explains approximately 4.8% of the variance in the authoritarian values scale for Germany, after accounting for the number of predictors. While statistically significant, this indicates that the model only explains a small portion of the variability in authoritarian values. For the second model, R-Squared adjusted value is similar at 0.050 (~5%), but it explains a bit more variability than the first model. AIC, BIC, and Log.Lik are all used to measure the goodness of fit of a model while penalizing for complexity. AIC and BIC are slightly lower for the second model, indicating that it is better than the first model. Log.Lik is higher (less negative) for the second model, so it is preferred to the first model. Overall, the second model is the best one to use/evaluate. Task 2
Now generate the model4 interaction plot that we did in the tutorial, but again using the German data instead of the French. Interpret.
interaction_plot <- effect("polID*religious", model4, na.rm=TRUE)
plot(interaction_plot,
main="Interaction effect",
xlab="Religiousness",
ylab="Authoritarian attitudes scale")
interaction_plot##
## polID*religious effect
## religious
## polID 0 2 5 8 10
## Left 56.40706 57.56775 59.30879 61.04983 62.21053
## Moderate 59.85063 61.66176 64.37844 67.09513 68.90626
## Right 60.60237 63.35032 67.47224 71.59416 74.34211## Interpretation: When looking at the slopes of each line, they do not look parallel. pollID = Moderate and pollID = Right look slightly more parallel to each other than pollID = Left, but the slopes of all three lines are clealry different. This suggests that an interaction effect is present between the variables of religiousness, political affiliation, and authoritarian value scale score; with religiousness and political affiliation influencing authoritarian value scale score.This makes sense, since according to model fit metrics, the second model in question 1 (interaction accounted for) has better goodness of fit than the first model (interaction not accounted for). In Germany, higher religiousness and right-wing ideology seem to be associated with the highest authoritarian value scale scores (~75), while lower religiousness and left-wing ideology seem to be associated with lower authoritarian value scale scores (~>60).Task 3
Use data for the Netherlands and the variable coding for model5 and model6 from the tutorial (i.e., both for the cleaning & recode, as well as the linear model formulas). Do a modelsummary table displaying both model outputs. Interpret the coefficients for the MLR without the interaction (i.e., the first displayed model), and interpret model fit metrics for both models.
netherlands_data <- read_fst("netherlands_data.fst")
nf <- netherlands_datanf$weight <- nf$dweight * nf$pweight
survey_design <- svydesign(ids = ~1, data = nf, weights = ~weight)nf <- nf %>%
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))) %>%
# Apply the reverse coding
mutate(across(c("behave", "secure", "safety", "tradition", "rules"), ~ 7 - .x ))
# Now you can calculate 'schwartzauth' after the NA recoding
nf$auth <- scales::rescale(nf$behave +
nf$secure +
nf$safety +
nf$tradition +
nf$rules, to=c(0,100), na.rm=TRUE)
nf <- nf %>% filter(!is.na(auth))nf <- nf %>%
mutate(religion = case_when(
rlgblg == 2 ~ "No",
rlgblg == 1 ~ "Yes",
rlgblg %in% c(7, 8, 9) ~ NA_character_,
TRUE ~ as.character(rlgblg)
))
# check
table(nf$religion)##
## No Yes
## 10913 6750nf <- nf %>%
mutate(ID = case_when(
lrscale >= 0 & lrscale <= 4 ~ "Left",
lrscale >= 6 & lrscale <= 10 ~ "Right",
lrscale > 10 ~ NA_character_, # Set values above 10 as NA
TRUE ~ NA_character_ # Ensure value 5 and any other unexpected values are set as NA
))
table(nf$ID)##
## Left Right
## 5449 7010nf <- nf %>%
mutate(
age = ifelse(agea == 999, NA, agea),
# Recoding cohort variable, setting years before 1930 and after 2000 to NA
cohort = ifelse(yrbrn < 1930 | yrbrn > 2000, NA, yrbrn),
# Recoding generational cohorts based on year of birth
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) # Keeping other values as character if they do not fit the ranges
),
# Converting cohort to a factor with labels
gen = factor(gen,
levels = c("1", "2", "3", "4"),
labels = c("Interwar", "Baby Boomers", "Gen X", "Millennials"))
)
table(nf$gen)##
## Interwar Baby Boomers Gen X Millennials
## 3771 6147 4548 2730model5 <- lm(auth ~ religion + ID + gen, data = nf, weights = weight)
model6 <- lm(auth ~ religion + ID + gen + religion*gen, data = nf, weights = weight)
modelsummary(
list(model5, model6),
fmt = 1,
estimate = c( "{estimate} ({std.error}){stars}",
"{estimate} ({std.error}){stars}"),
statistic = NULL,
coef_omit = "Intercept")| (1) | (2) | |
|---|---|---|
| religionYes | 7.2 (0.3)*** | 5.7 (0.7)*** |
| IDRight | 4.2 (0.3)*** | 4.3 (0.3)*** |
| genBaby Boomers | −5.2 (0.4)*** | −5.9 (0.6)*** |
| genGen X | −7.7 (0.4)*** | −8.8 (0.6)*** |
| genMillennials | −8.4 (0.5)*** | −9.7 (0.6)*** |
| religionYes × genBaby Boomers | 1.1 (0.8) | |
| religionYes × genGen X | 2.3 (0.9)** | |
| religionYes × genMillennials | 2.9 (1.0)** | |
| Num.Obs. | 12116 | 12116 |
| R2 | 0.124 | 0.125 |
| R2 Adj. | 0.124 | 0.125 |
| AIC | 101219.3 | 101213.5 |
| BIC | 101271.2 | 101287.5 |
| Log.Lik. | −50602.672 | −50596.757 |
| RMSE | 15.27 | 15.26 |
## Interpreting Coefficients (No Interaction: ReligionYes has a coefficient of 7.2, which indicates that on average, religious individuals score 7.2 units higher on the authoritarian values scale than non-religious individuals. Likewise, IDRight has a coefficient of 4.2, which indicates that on average, politically right-leaning individuals score 4.2 units higher on the authoritarian values scale than politically left-leaning individuals. As for the generations, Baby Boomers score about 5.2 units lower, Gen Xer's score about 7.7 units lower, and Millennials score about 8.4 units lower on the authoritarian values scale than the Interwar generation (the reference category). These findings suggest that overall, authoritarian attitudes have been declining in the Netherlands which each coming generation. However, identifying as politically right-wing or religious is associated with higher scores on the authoritarian values scale. All five categories have three asterisks, indicating that p < 0.001 and there is therefore less than a 0.1% probability that the observed results are due to chance (so we do not reject the null).## Interpreting Model Fit Metrics: R-Squared Adjusted is 0.124 for the first model, indicating that 12.4% of the variance in authoritarian value scale scores is explained by our variables (generation, religion, and political ideology). For the second model, R-Squared Adjusted is 0.125, so about 12.5% of variance in authoritarian value scale scores is explained by our variables. These percentages are essentially the same, with the second model explaining only a small portion more of variance than the first model. AIC is slightly lower for the second model, but BIC is slightly higher.Log.Lik is slightly higher for the second model (less negative). Overall, this indicates that the second model has better goodness of fit than the first model, and is therefore the better for evaluation. Again, though, the difference is minimal, perhaps only due to the complexity difference between models. Task 4
Produce the model7 interaction plot from the tutorial, but again using the Netherlands data. Interpret.
model7 <- lm(auth ~ + cohort + ID + cohort*ID, data = nf, weights = weight)
interact_plot(model7, pred = cohort, modx = ID, jnplot = TRUE)
##Interpretation: The slopes of the two lines are not parallel, with the slope for ID = Right (~30 degrees) being at a greater angle than ID = Left (~20 degrees). This implies that there is an interaction effect present between the variables of political affiliation, generation (cohort), and authoritarian value scale score; with cohort and political affiliation influencing authoritarian value scale score. In this case, it seems that in the Netherlands, later generations (ex. millennials) who identify with left-wing ideology produce the lowest authoritarian value scale scores (~55); while earlier generations (boomers) who identify with right-wing ideology produce the highest authoritarian value scale scores (~70+). Task 5
Produce the model8 interaction plot from the tutorial, but again using the Netherlands data. Interpret.
nf <- nf %>%
mutate(
religious = case_when(
rlgdgr %in% c(77, 88, 99) ~ NA_real_,
TRUE ~ rlgdgr
)
)
model8 <- lm(auth ~ religious + ID + religious*ID, data = nf, weights = weight)
interact_plot(model8, pred = religious, modx = ID, jnplot = TRUE)
##Interpretation: Looking at the graph, the slopes of the two lines for ID = Left and ID = Right look mostly parallel. ID = Right is at a slightly greater angle than ID = Left, they are quite similar. This would imply that in the Netherlands, there is no interaction effect present between religiousness, political affiliation, and authoritarian value scale score. On average, authoritarian value scale scores are slightly higher for those who identify as politically right-wing (~60-75 rather than ~55-65), but being religious does not seem to impact authoritarian value scale score. This is different from Germany, where religiousness seemed to have an interaction effect on authoritarian value scale scores.