eohi/.history/eohi1/regression e1 - ehi x sex x age_20251020174522.r
2025-12-23 15:47:09 -05:00

39 lines
880 B
R

options(scipen = 999)
library(dplyr)
library(car)
library(lmtest)
library(stargazer)
library(sandwich)
library(lmtest)
setwd("C:/Users/irina/Documents/DND/EOHI/eohi1")
df <- read.csv("ehi1.csv")
data <- df %>%
select(eohiDGEN_mean, ehi_global_mean, demo_sex, demo_age_1) %>%
filter(demo_sex != "Prefer not to say")
str(data)
colSums(is.na(data))
sapply(data, class)
# Create dummy variable for sex (0 = Male, 1 = Female)
data$sex_dummy <- ifelse(data$demo_sex == "Female", 1, 0)
# Verify the dummy coding
print(table(data$demo_sex, data$sex_dummy))
#descriptives
# Descriptives for age
print(summary(data$demo_age_1))
sd(data$demo_age_1, na.rm = TRUE)
# Descriptives for sex (frequency table)
print(table(data$demo_sex))
print(prop.table(table(data$demo_sex)))
# Descriptives for sex dummy variable
print(table(data$sex_dummy))