Proxy Variables and Nonparametric Identification of Causal Effects

10 Pages Posted: 18 Jul 2016

See all articles by Xavier de Luna

Xavier de Luna

University of Umea - Department of Economics

Philip Fowler

University of Umea

Per Johansson

IFAU - Institute for Labour Market Policy Evaluation; Uppsala University - Department of Economics; IZA Institute of Labor Economics

Abstract

Proxy variables are often used in linear regression models with the aim of removing potential confounding bias. In this paper we formalise proxy variables within the potential outcome framework, giving conditions under which it can be shown that causal effects are nonparametrically identified. We characterise two types of proxy variables and give concrete examples where the proxy conditions introduced may hold by design.

Keywords: average treatment effect, observational studies, potential outcomes, unobserved confounders

JEL Classification: C14

Suggested Citation

de Luna, Xavier and Fowler, Philip and Johansson, Per, Proxy Variables and Nonparametric Identification of Causal Effects. Available at SSRN: https://ssrn.com/abstract=2810468 or http://dx.doi.org/10.2139/ssrn.2810468

Xavier De Luna (Contact Author)

University of Umea - Department of Economics ( email )

Umeå University
Umea, SE - 90187
Sweden

Philip Fowler

University of Umea ( email )

Samhallsvetarhuset, Plan 2
Umea University
Umeå, SE 901 87
Sweden

Per Johansson

IFAU - Institute for Labour Market Policy Evaluation ( email )

Box 513
751 20 Uppsala
Sweden
+ 46 18 471 70 86 (Phone)
+ 46 18 471 70 71 (Fax)

Uppsala University - Department of Economics ( email )

Uppsala, 751 20
Sweden

IZA Institute of Labor Economics

P.O. Box 7240
Bonn, D-53072
Germany

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

Paper statistics

Downloads
113
Abstract Views
636
rank
307,569
PlumX Metrics