====== Cluster Sampling ====== Sometimes it is cheaper to 'cluster' the sample in some way e.g. by selecting respondents from certain areas only, or certain time-periods only. (Nearly all samples are in some sense 'clustered' in time -- although this is rarely taken into account in the analysis.) ===== Animation ===== Once a cluster is sampled, all its elements will be chosen. ===== R code =====

library(animation)
saveHTML({
    ani.options(nmax = 30, interval = 1)
    par(mar = rep(1, 4))
    sample.cluster(col = c("bisque", "white"))
}, img.name = "sample_cluster", htmlfile = "sample_cluster.html", 
    ani.height = 450, ani.width = 600, outdir = getwd(), title = "Demonstration of the cluster sampling", 
    description = c("Once a cluster is sampled, all its elements will be\nchosen."))