options(scipen = 999)

library(dplyr)

setwd("C:/Users/irina/Documents/DND/EOHI/eohi1")

df <- read.csv("ehi1.csv")

data <- df %>%
  select(eohiDGEN_mean, ehi_global_mean, demo_edu) %>%
  mutate(demo_edu = as.factor(demo_edu))

# examine data object
str(data)
colSums(is.na(data))
sapply(data, class)
levels(data$demo_edu)

data$demo_edu <- factor(data$demo_edu, levels = c(
  "High School (or equivalent)",
  "Trade School (non-military)", 
  "College Diploma/Certificate",
  "University - Undergraduate",
  "University - Graduate (Masters)",
  "University - PhD",
  "Professional Degree (ex. JD/MD)"
))

levels(data$demo_edu)
# Create dummy variables
dummy_vars <- model.matrix(~ demo_edu - 1, data = data)
dummy_df <- as.data.frame(dummy_vars)

# Rename columns with meaningful names (excluding reference level)
colnames(dummy_df) <- c(
  "edu_highschool",           # reference level (will be dropped)
  "edu_trade",
  "edu_college", 
  "edu_uni_undergrad",
  "edu_uni_masters",
  "edu_uni_phd",
  "edu_prof"
)
# Add to your data
data <- cbind(data, dummy_df)