|
Abstract:
|
Many observational studies of causal effects occur in settings with clustered treatment assignment. In studies of this type, treatment is applied to entire clusters of units. For example, an educational intervention might be administered to all the students in a school. In this paper, we develop a matching algorithm for multilevel data based on a network flow algorithm. Earlier work on multilevel matching relied on integer programming, which allows for balance targeting on specific covariates, but can be slow with larger data sets. While we cannot target balance on specific covariates, our algorithm is quite fast and scales easily to larger data sets. We also consider complications that arise from the common support assumption. We evaluate our match method by recovering an experimental benchmark from a group randomized trial in North Carolina. We replace the controls from the RCT with the population of schools excluded from the study. We apply our matching method to replicate the balance produced by randomization. We find that while matching can recover the experimental benchmark, the success depends on the form of the match.
|
