Sampling for evaluation. Issues and strategies for community-based HIV prevention programs

Sampling methods are an important issue in the evaluation of community-based HIV prevention initiatives because it is through responsible sampling procedures that a valid model of the population is produced and reliable estimates of behavior change determined. This article provides an overview on sampling with particular focus on the needs of community-based organizations (CBOs). As these organizations continue to improve their capacity for sampling and program evaluation activities, comparisons across CBOs can become more rigorous, resulting in valuable information collectively regarding the effectiveness of particular HIV prevention initiatives. The author reviews several probability and non-probability sampling designs; discusses bias, cost, and feasibility factors in design selection; and presents six guidelines designed to encourage community organizations to consider these important sampling issues as they plan their program evaluations.