Learning More From Educational Intervention Studies : Estimating Complier Average Causal Effects in a Relevance Intervention

Abstract

An emerging literature demonstrates that relevance interventions, which ask students to produce written reflections on how what they are learning relates to their lives, improve student learning outcomes. As part of a randomized evaluation of a relevance intervention (N D 1,978 students from 82 ninthgrade classes), we used Complier Average Causal Effects (CACE) to identify the effect of the intervention on participants who were assigned to the intervention group and were actually compliant with the intervention (i.e., treatment fidelity or compliance). Results revealed larger differences for compliers than noncompliers, although this impact depended on several factors. Implications for the application of CACE models in educational interventions, in general, and relevance interventions, in particular, are discussed.