The Role of the Propensity Score in Fixed Effect Models

52 Pages Posted: 16 Jul 2018 Last revised: 21 Apr 2023

See all articles by Dmitry Arkhangelsky

Dmitry Arkhangelsky

Centre for Monetary and Financial Studies (CEMFI)

Guido W. Imbens

Stanford Graduate School of Business

Date Written: July 2018

Abstract

We develop a new approach for estimating average treatment effects in the observational studies with unobserved cluster-level heterogeneity. The previous approach relied heavily on linear fixed effect specifications that severely limit the heterogeneity between clusters. These methods imply that linearly adjusting for differences between clusters in average covariate values addresses all concerns with cross-cluster comparisons. Instead, we consider an exponential family structure on the within-cluster distribution of covariates and treatments that implies that a low-dimensional sufficient statistic can summarize the empirical distribution, where this sufficient statistic may include functions of the data beyond average covariate values. Then we use modern causal inference methods to construct flexible and robust estimators.

Suggested Citation

Arkhangelsky, Dmitry and Imbens, Guido W., The Role of the Propensity Score in Fixed Effect Models (July 2018). NBER Working Paper No. w24814, Available at SSRN: https://ssrn.com/abstract=3214360

Dmitry Arkhangelsky (Contact Author)

Centre for Monetary and Financial Studies (CEMFI) ( email )

Casado del Alisal 5
28014 Madrid
Spain

Guido W. Imbens

Stanford Graduate School of Business ( email )

655 Knight Way
Stanford, CA 94305-5015
United States

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

Paper statistics

Downloads
34
Abstract Views
402
PlumX Metrics