# Statistics Lab / ferdo — synthetic data (no real student records)
# Save stats_synthetic.csv in your working directory.
d <- read.csv("stats_synthetic.csv", stringsAsFactors = TRUE)
stopifnot(nrow(d) == 36, all(c("score_pre","score_post","group") %in% names(d)))
# Groups are observational labels: differences cannot establish a treatment effect.

m <- lm(score_post ~ study_hours, data=d)
summary(m)
plot(m, which=1)
predict(m, newdata=data.frame(study_hours=4),
        interval="prediction")
range(d$study_hours)