Representative Sampling in Humanitarian Evaluation

Evaluations are meant to provide trustworthy feedback on a program – for real-time evaluations this feedback is crucial to being able to make course corrections, for ex-post evaluations this feedback can demonstrate effectiveness and accountability to both donors and affected people, and inform future programs. As evaluation professionals, we aim to collect data that is representative of a population at a certain time, and which can be used to compare with other snapshots in time (for impact assessment or trend analysis). If the information is to be used for advocacy purposes, this is especially important as entire studies have been discounted because the sampling framework was not deemed to be representative.