Evaluation of the Validity and Precision of the Multiple-Cutoff Regression Discontinuity Design: A Within-Study Comparison

• In Event: Program Evaluation Methods: Implementation and Impact Measurements

Abstract

Different cutoffs may be used in a multisite intervention that assigns individuals or units to treatment on a need basis, yielding a multiple cutoff regression discontinuity design (MCRD). The availability of multiple cutoffs allows estimation of a pooled average treatment effect across cutoffs and/or individual estimates at each cutoff location, allowing for the possibility of heterogeneous treatment effects. The purpose of this study is to examine the extent to which the two multiple-cutoff RD estimates (i.e., derived from a conventional pooling method and a multilevel pooling method) compared, in terms of validity and precision, to the impact estimate obtained from a randomized control trial (RCT). Implications for program evaluation design theory and practice are discussed.

Authors

• HyeonJin Yoon, University of Nebraska-Lincoln

• Keith Zvoch, University of Oregon

• Keith Smolkowski, Oregon Research Institute

• Ben Clarke, University of Oregon