A Software Tutorial for Matching in Clustered Observational Studies
Abstract
Many interventions occur in settings where treatments are applied to groups. For example, a math intervention may be implemented for all students in some schools and withheld from students in other schools. When such treatments are non-randomly allocated, researchers can use statistical adjustment to make treated and control groups similar in terms of observed characteristics. Recent work in statistics has developed a form of matching, known as multilevel matching, that is designed for contexts where treatments are clustered. In this article, we provide a tutorial on how to analyze clustered treatment using multilevel matching. We use a real data application to explain the full set of steps for the analysis of a clustered observational study.
Matthew Lenard
PhD candidate in Education Policy & Program Evaluation
I am a Ph.D. candidate at the Harvard Graduate School of Education (HGSE) in its Education Policy and Program Evaluation concentration. My research centers on using causal inference research designs to measure the impacts of education programs and policies. I typically study topics at the intersection of education and economics, but also draw from the traditions of sociology and political science. My current projects focus on career and technical education, peer effects, school choice, and teacher labor markets.