Question

1. Why would a cluster sample lead to lower data collection costs as compared to a simple random sample or a stratified probability sample.

Answer 1

We know that clusters are constructed such that sampling unites are heterogeneous within clusters and homogeneous among the clusters. But in case of stratified sampling we divide whole heterogeneous population into small subpopulations which is consisted with homogeneous elements. here subpopulations are called strata. So we can say sampling units are homogeneous in a stratum but strata are heterogeneous to each other. so we see each cluster can represent a whole population while drawing sampling units from each strata represent it. In stratified sampling, a random sample is drawn from each of the strata, whereas in cluster sampling only the selected clusters are sampled. We can get higher sampling efficiency which leads to reduce data collection cost. The tendency of individuals within a cluster is to have similar characteristics and with a cluster sample. And in the case of simple random sampling we have to collect various type of sample units from a population although It can not cover the whole characteristics of the total population. Then we need to collect data randomly and for this data collection cost would be high in the sampling technique. then We can make a cost sequence cluster sampling< stratified sampling<simple random sampling.