Abstract
There is probably no subject related to evaluation causing as much confusion and unnecessary anxiety as the matter of sampling. In this article we provide some general guidelines or principles to keep in mind with respect to the number of program participants (or number of program components) to be included in a formal evaluation. We do not provide a description of the methods for the actual selection of a sample, for there are many good descriptions already available in other sources. Our goal here is to provide a very practical way of thinking about sampling as an essential part of program evaluation. Our most important point is that sampling is an essential part of the “science” of program evaluation, but the reasoning underlying the use of sampling is straightforward and should be part of sound program planning and development. Careful thought about these issues at the outset of a project can greatly enhance the generalizability and replicability of project results.
Get full access to this article
View all access options for this article.