|Title:||Identifying Best Practices for Estimating Average Treatment Effects in Cluster Randomized Trials: Estimands, Estimators, and Estimates|
|Principal Investigator:||Weiss, Michael||Awardee:||MDRC|
|Program:||Statistical and Research Methodology in Education [Program Details]|
|Award Period:||3 years (07/1/2022 - 06/30/2025)||Award Amount:||$898,275|
|Type:||Methodological Innovation||Award Number:||R305D220046|
Co-Principal Investigator: Miratrix, Luke
The purpose of this grant is to provide guidance to applied researchers on the best estimands and estimators of those estimands for analyses of cluster randomized control trials (CRTs). The researchers will use Monte Carlo simulations based on actual CRT design features to gauge the comparative accuracy of the estimators and their standard errors. The research team will also conduct secondary analyses of real data from several CRTs in order to illustrate differences in practice among the numerical values of the estimators and standard errors, as well as the interpretations of the estimators, given their underlying estimands. The research team will publish a synthesis of the results online and as a peer-reviewed journal manuscript. The researchers will also publish a user-friendly R package that will be able to conduct analyses to provide all the estimators investigated as part of the grant work. They will present research findings and the software package at conferences and at workshops on using the software.