In cluster sampling, how is the sample drawn?

• A. Divide the population into groups (clusters) and select all members in one or more clusters
• B. Randomly select individuals from the entire population
• C. Divide the population into groups (clusters) and select all of the members in one or more, but not all, of the clusters
• D. Randomly select clusters until a quota is filled

Answer: (C)

In cluster sampling, you start by dividing the population into groups called clusters, then randomly select some of those clusters and collect data from every member within the chosen clusters. This approach is efficient when the population is spread over a wide area or difficult to list as individuals, because it lowers travel and administrative costs by surveying whole clusters instead of individuals scattered everywhere. The description that best fits this method is dividing the population into clusters, then taking all members from one or more of the selected clusters but not from every cluster in the population.

The other descriptions describe different sampling methods: choosing individuals randomly from the entire population aligns with simple random sampling; selecting clusters until a quota is reached corresponds to quota sampling; and simply picking one or a few clusters and surveying everyone in them without specifying that only some clusters are used is less precise about the sampling design.