During this discussion, your evaluator will be using the term "statistical significance." This is a very important concept when comparing quantitative outcomes, such as participants' communication skills both pre- and post-intervention. Statistically significant findings are not likely to have occurred by chance; they are "real" and worth attending to. Your evaluator should be clear as to which findings are and are not statistically significant.
Establishing statistical significance is only the first step; you and your evaluator should also seek to interpret the practical significance of statistically significant findings. Are these findings "large," or "small"? How do they compare with findings from other behavioral intervention programs?
Equally important (though often undervalued) are non-statistically significant findings. These are findings in which the change is so small that it could have occurred by chance. As a provider, you will want to know if desired outcomes are not achieved. This could help you decide whether program improvements are necessary.
- Muraskin, L. (1993). Understanding evaluation: The way to better prevention programs. Washington, DC: U.S. Department of Education
- Significance in Statistics and Surveys, The Survey System
- U.S. Department of Health and Human Services, Administration for Children and Families, Office of Planning, Research & Evaluation. The Program Manager's Guide to Evaluation Glossary.