Replicating Experimental Impact Estimates Using a Regression Discontinuity Approach
Assessing New Uses of Regression Discontinuity (RD) Designs: Producing Broader Evaluations of Education and Training Interventions
National Science Foundation
This report attempts to replicate the estimated impacts from experimental studies of two different education interventions using a regression discontinuity design. In each case, the estimated impact of the intervention based on the regression discontinuity design was not significantly different from the experimental impact estimate, though the magnitude of the differences between the point estimates of impacts from the two designs sometimes was nontrivial.