Nonparametric Regression with Stochastic Boundary and Regression Discontinuity with Endogenous Cutoff

13 Pages Posted: 23 Jan 2020

See all articles by Jiafeng Chen

Jiafeng Chen

Harvard University, Harvard College, Students; Harvard University, Faculty of Arts and Sciences, Students

Date Written: December 28, 2019

Abstract

We augment the usual regression discontinuity design model by considering an endogenously chosen cutoff, perhaps chosen to maximize certain criterion that the treatment provider has. This regime faces the challenge that, conditional on realization of the cutoff, observations are no longer i.i.d. We develop conditions under which an asymptotic expansion of the locally linear estimator contains a bias term caused by the endogeneity of order op(h2 +1/√nh). The lower order bias justifies the usual optimal bandwidth selection and bias correction procedures in this setting, though it places constraints on the maximal degree of undersmoothing.

Keywords: Regression discontinuity, Nonparametric regression

JEL Classification: C10, C14

Suggested Citation

Chen, Jiafeng and Chen, Jiafeng, Nonparametric Regression with Stochastic Boundary and Regression Discontinuity with Endogenous Cutoff (December 28, 2019). Available at SSRN: https://ssrn.com/abstract=3510899 or http://dx.doi.org/10.2139/ssrn.3510899

Jiafeng Chen (Contact Author)

Harvard University, Faculty of Arts and Sciences, Students ( email )

Cambridge, MA
United States

Harvard University, Harvard College, Students ( email )

Cambridge, MA
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
107
Abstract Views
675
Rank
456,834
PlumX Metrics