Identifying Treatment Effects in the Presence of Confounded Types

53 Pages Posted: 6 Nov 2017 Last revised: 15 Feb 2019

See all articles by Désiré Kédagni

Désiré Kédagni

Iowa State University, Department of Economics

Date Written: November 2, 2017

Abstract

In this paper, I consider identification of treatment effects when the treatment is endogenous. The use of instrumental variables is a popular solution to deal with endogeneity, but this may give misleading answers when the instrument is invalid. I show that when the instrument is invalid due to correlation with the first stage unobserved heterogeneity, a second (also possibly invalid) instrument helps partially identify not only the local average treatment effect but also the entire potential outcomes distributions for compliers. I exploit the fact that the distribution of the observed outcome in each group defined by the treatment and the instrument is a mixture of the distributions of interest. I write the identified set in the form of conditional moment inequalities, and provide an easily implementable inference procedure. Under some (testable) tail restrictions, the potential outcomes distributions are point-identified for compliers. Finally, I illustrate my methodology on data from the National Longitudinal Survey of Young Men to estimate returns to college using college proximity as (potential) instrument. I fi nd that a college degree increases the average hourly wage of the compliers by 38-79%.

Keywords: Potential outcome, instrumental variable, LATE, compliers, mixture models

JEL Classification: C16, C21, C25, C26

Suggested Citation

Kédagni, Désiré, Identifying Treatment Effects in the Presence of Confounded Types (November 2, 2017). Available at SSRN: https://ssrn.com/abstract=3064230 or http://dx.doi.org/10.2139/ssrn.3064230

Désiré Kédagni (Contact Author)

Iowa State University, Department of Economics ( email )

518 Farm House Lane
467 Heady Hall
Ames, IA 50011
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
143
rank
197,184
Abstract Views
787
PlumX Metrics