This article is intended to assist teachers and researchers in designing studies that examine the efficacy of a particular intervention or strategy with students with sensory disabilities. Ten research designs that can establish causal inference (the ability to attribute any effects to the intervention) with and without randomization are discussed.

The Communities In Schools (CIS) Model of Integrated Student Supports aims to reduce dropout rates by providing students with integrated and tiered support services based on their levels of need. The model includes preventive services that are available to all students (Level 1 services) as well as intensive, targeted, and sustained services…

This report summarizes the complex research literature on quantitative methods for assessing how impacts of educational interventions on instructional practices and student learning differ across students, educators, and schools. It also provides technical guidance about the use and interpretation of these methods. The research topics addressed…

Educational researchers frequently study the impact of treatments or interventions on educational outcomes. However, when observational or quasiexperimental data are used for such investigations, selection bias can adversely impact researchers' abilities to make causal inferences about treatment effects. One way to deal with selection bias is to…

This methodological brief is designed to provide both program operators and researchers with practical advice about how to assess a program's implementation and impact. Adapted from an article that first appeared in "The Handbook of Youth Mentoring" (DuBois and Karcher, ed. 2005), the brief focuses on the evaluation of mentoring programs, but the…

Education research rarely lends itself to large scale experimental research and true randomization, leaving the researcher to quasi-experimental designs. The problem with quasi-experimental research is that underlying factors may impact group selection and lead to potentially biased results. One way to minimize the impact of non-randomization is…