Inequality in categorical models
Example 4.2.b of Mize and Han (2025), in R
Because the statistic is built from predictions, it works the same way after a binary logit, where the predictions are probabilities. This example summarizes several nominal and binary predictors of conservative identification at once: gender, race-ethnicity, and subjective class. The same example in Stata is on the meinequality page.
Load and prepare the data
library(haven) # Read Stata data
library(marginaleffects) # Marginal effects and hypotheses
source("https://raw.githubusercontent.com/tdmize/Rfunctions/main/ME_helper_functions.R")
gss <- read_dta("https://tdmize.github.io/data/data/cda_gss.dta")
gss <- gss[gss$year == 2021, ]
vars <- c("conserv", "race4", "woman", "class", "age")
gss <- gss[complete.cases(gss[vars]), vars]
fvars <- c("conserv", "race4", "woman", "class")
gss[fvars] <- lapply(gss[fvars], as_factor)
gss <- droplevels(gss)
nrow(gss)[1] 3608
Fit the model
conmod <- glm(conserv ~ woman + race4 + class,
family = binomial("logit"), data = gss)ME inequality for each predictor
Each predictor gets its own weights. Gender:
w_woman <- meineq_weights(conmod, woman)
avg_comparisons(conmod,
variables = list(woman = "pairwise"),
hypothesis = ~ I(weighted.mean(abs(x), w_woman))) Estimate Std. Error z Pr(>|z|) S 2.5 % 97.5 %
0.0695 0.0156 4.47 <0.001 16.9 0.039 0.1
Type: response
Race-ethnicity:
w_race <- meineq_weights(conmod, race4)
avg_comparisons(conmod,
variables = list(race4 = "pairwise"),
hypothesis = ~ I(weighted.mean(abs(x), w_race))) Estimate Std. Error z Pr(>|z|) S 2.5 % 97.5 %
0.108 0.0135 7.99 <0.001 49.4 0.0814 0.134
Type: response
Subjective class:
w_class <- meineq_weights(conmod, class)
avg_comparisons(conmod,
variables = list(class = "pairwise"),
hypothesis = ~ I(weighted.mean(abs(x), w_class))) Estimate Std. Error z Pr(>|z|) S 2.5 % 97.5 %
0.0122 0.0174 0.701 0.484 1.0 -0.0219 0.0464
Type: response
Class has no overall effect on conservative identification. Racial-ethnic groups differ by about 11 percentage points on average. For a binary variable such as woman the ME inequality is simply the absolute value of its marginal effect, which puts binary and multi-category predictors on the same footing for comparison.