A0350
Title: Tests for many treatment effects in regression discontinuity panel data models
Authors: Georg Keilbar - Humboldt-University of Berlin (Germany) [presenting]
Likai Chen - Washington University in Saint Louis (United States)
Liangjun Su - Tsinghua University (China)
Weining Wang - University of Groningen (Netherlands)
Abstract: Numerous studies use regression discontinuity design (RDD) for panel data by assuming that the treatment effects are homogeneous across all individuals/groups and pooling the data to- together. It is unclear how to test for the significance of treatment effects when the treatments vary across individuals/groups, and the error terms may exhibit complicated dependence structures. The estimation and inference of multiple treatment effects are examined when the errors are not independent and identically distributed, and the treatment effects vary across individuals/groups. A simple analytical expression is derived for approximating the variance-covariance structure of the treatment effect estimators under general dependence conditions and proposes two test statistics: one is to test for the overall significance of the treatment effect and the other for the homogeneity of the treatment effects. It is found that in the Gaussian approximations of the test statistics, the dependence structures in the data can be safely ignored due to the localized nature of the statistics. This has the important implication that the simulated critical values can be easily obtained. Simulations demonstrate the tests have superb size control and reasonable power performance in finite samples regardless of the presence of strong cross-section dependence or/and weak serial dependence in the data. The tests on two datasets are applied, and significant overall treatment effects are found in each case.
