simulate_clustered_data.R

CreateClusteredData <- function(num.groups, sample.size, beta, randomize.by.group = FALSE){
    individual <- 1:sample.size # index for individuals
    group <- sample(1:num.groups, size = sample.size, replace = TRUE) # randomly assign everyone to a group
    group.effect <- rnorm(num.groups) # create a group-specific effect
    eta <- group.effect[group] # give each individual their group-specific effect
    epsilon <- rnorm(sample.size) # given each individual an individual-specific effect
    if (randomize.by.group){
        group.trt.assignment <- rbinom(num.groups, 1, 0.5) 
        trt <- group.trt.assignment[group]
    } else {
        trt <- rbinom(sample.size, 1, 0.5)
    }
    y <- beta * trt + epsilon + eta 
    data.frame(y, individual, group, trt, epsilon, eta)
}