Methods for the analysis of pair-matched binary data from school-based intervention studies

In the evaluation of school-based intervention programs, students' knowledg e, behavior; and attitudes about a particular issue are typically assessed before and after the intervention. The effectiveness of the intervention ca n then be gauged by comparing these "pre-treatment" and "post-treatment" re sponses. In the most rigorous evaluations, students ape randomized to the i ntervention or control group. However; instead of randomizing individual st udents to treatment, most school-based studies rely on clustered randomizat ion schemes. This is generally operationalized as the assignment of schools to treatment condition, although students within schools serve as the unit s of observation. Because there tends to be positive correlation between re sponses from students at the same school, the assumption of statistical ind ependence is violated; hence, application of statistical tests that ignore this correlation can result in biased significance levels. This paper explo res two statistical methods that account for this correlation in analyzing binary data. A proposal for adapting these methods for application to match ed pairs data is presented. The performance of the methods is evaluated via simulation study.