Bartalotti, Otavio; Brummet, Quentin
WP #15021, August 2015
Regression Discontinuity designs are popular due to their attractive properties for estimating causal ffects under transparent assumptions. Nonetheless, most popular procedures assume i.i.d. data, which is unreasonable in common applications. To relax this assumption, we derivethe properties of traditional estimators in a setting that incorporates clustering at the level of the running variable, and propose an accompanying optimal-MSE bandwidth selection rule. Simulation results demonstrate that falsely assuming data are i.i.d. may lead to bandwidths that are "too small." We apply our procedure to analyze the impact of Low-Income Housing Tax Credits on neighborhood characteristics and low-income housing supply.
JEL Classification: C13, C14, C21