Which sampling method divides the population into subgroups and draws random samples from each subgroup?

• A. Simple random sampling
• B. Systematic random sampling
• C. Stratified random sampling
• D. Cluster sampling

Answer: (C)

Dividing the population into subgroups that share a characteristic and then drawing random samples from each subgroup is stratified random sampling. Each subgroup, or stratum, might be based on something like age, region, or gender. By sampling from every stratum, the overall sample mirrors the population’s composition across those characteristics, which helps ensure representation and reduces the chance that a group is under- or over-represented. It also gives more precise estimates because variability within each stratum is typically smaller than across the whole population, and you can combine the results from all strata in a principled way.

For context, the simple random approach mixes everyone together, so some subgroups can end up underrepresented by chance. Systematic sampling picks every k-th item from an ordered list, which doesn’t guarantee representation of different subgroups. Cluster sampling groups the population into clusters and then samples whole clusters, which means you’re not necessarily sampling within each subgroup across the whole population.