Identification of Treatment Effects under Conditional Partial Independence

37 Pages Posted: 1 Aug 2017

See all articles by Matthew Masten

Matthew Masten

Duke University - Department of Economics

Alexandre Poirier

Georgetown University - Department of Economics

Date Written: July 29, 2017

Abstract

Conditional independence of treatment assignment from potential outcomes is a commonly used but nonrefutable assumption. We derive identified sets for various treatment effect parameters under nonparametric deviations from this conditional independence assumption. These deviations are defined via a conditional treatment assignment probability, which makes it straightforward to interpret. Our results can be used to assess the robustness of empirical conclusions obtained under the baseline conditional independence assumption.

Keywords: Treatment Effects, Conditional Independence, Unconfoundedness, Selection on Observables, Sensitivity Analysis, Nonparametric Identification, Partial Identification

JEL Classification: C14, C18, C21, C51

Suggested Citation

Masten, Matthew and Poirier, Alexandre, Identification of Treatment Effects under Conditional Partial Independence (July 29, 2017). Available at SSRN: https://ssrn.com/abstract=3010774 or http://dx.doi.org/10.2139/ssrn.3010774

Matthew Masten (Contact Author)

Duke University - Department of Economics ( email )

Durham, NC
United States

HOME PAGE: http://www.mattmasten.com

Alexandre Poirier

Georgetown University - Department of Economics ( email )

Washington, DC 20057
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
49
Abstract Views
402
PlumX Metrics