Sample Size Calculator.
A simple tool for determining the necessary sample size for proportion-based indicators in household surveys and baseline/endline evaluations, adjusting for the design effect of cluster sampling.
Design Effect (DEFF)
Most development surveys do not use Simple Random Sampling (SRS) because creating a listing of every individual in a region is cost-prohibitive. Instead, they use Cluster Sampling (e.g., picking villages first, then households within villages).
People living in the same village tend to be more similar to each other than to people in other villages. This homogeneity reduces the statistical information provided by each new respondent.
The Design Effect (DEFF) accounts for this loss of variance. A DEFF of 2.0 means you need twice as many people in your cluster sample to achieve the same precision as a simple random sample.