A maximum variation sample contains cases that are purposefully as different from each other as possible. This type of sampling is useful for examining range in large national or global programs.
Choosing sites that vary as much as possible along each of the criteria will allow the evaluator to investigate the particularities of each case as well as patterns that are shared across the variation.
In order to develop the sample, the evaluator must develop key criteria for identifying difference. For an agricultural research program, variation criteria may include: climate, soil features, rainfall, farming patterns, and level of government support.
This page is a stub (a minimal version of a page). You can help expand it. Click on Contribute Content or Contact Us to suggest additional resources, share your experience using the option, or volunteer to expand the description.