Regression Discontinuity Design with Continuous Measurement Error in the Running Variable

59 Pages Posted: 17 Jan 2017

See all articles by Laurent Davezies

Laurent Davezies

National Institute of Statistics and Economic Studies (INSEE) - Center for Research in Economics and Statistics (CREST)

Thomas Le Barbanchon

Bocconi university; Centre for Economic Policy Research (CEPR)

Multiple version iconThere are 2 versions of this paper

Date Written: January 2017

Abstract

Since the late 90s, Regression Discontinuity (RD) designs have been widely used to estimate Local Average Treatment Effects (LATE). When the running variable is observed with continuous measurement error, identification fails. Assuming nondifferential measurement error, we propose a consistent nonparametric estimator of the LATE when the discrepancy between the true running variable and its noisy measure is observed in an auxiliary sample of treated individuals, and when there are treated individuals at any value of the true running variable - two-sided fuzzy designs. We apply our method to estimate the effect of receiving unemployment benefits.

Keywords: Measurement error, regression discontinuity design, Unemployment insurance

JEL Classification: C14, C21, C51

Suggested Citation

Davezies, Laurent and Le Barbanchon, Thomas, Regression Discontinuity Design with Continuous Measurement Error in the Running Variable (January 2017). CEPR Discussion Paper No. DP11775. Available at SSRN: https://ssrn.com/abstract=2900192

Laurent Davezies (Contact Author)

National Institute of Statistics and Economic Studies (INSEE) - Center for Research in Economics and Statistics (CREST) ( email )

15 Boulevard Gabriel Peri
Malakoff Cedex, 1 92245
France

Thomas Le Barbanchon

Bocconi university ( email )

Via Sarfatti, 25
Milan, MI 20136
Italy

Centre for Economic Policy Research (CEPR) ( email )

London
United Kingdom

Register to save articles to
your library

Register

Paper statistics

Downloads
0
Abstract Views
168
PlumX Metrics