Use of Propensity Scores in Non-Linear Response Models: The Case for Health Care Expenditures

54 Pages Posted: 22 Jun 2008 Last revised: 29 Jun 2010

See all articles by Anirban Basu

Anirban Basu

University of Chicago - Department of Medicine

Daniel Polsky

Bloomberg School of Public Health, Department of Health Policy and Management, Johns Hopkins University; Johns Hopkins University - Carey Business School

Willard G. Manning

University of Chicago - Harris School of Public Policy

Date Written: June 2008

Abstract

Under the assumption of no unmeasured confounders, a large literature exists on methods that can be used to estimating average treatment effects (ATE) from observational data and that spans regression models, propensity score adjustments using stratification, weighting or regression and even the combination of both as in doubly-robust estimators. However, comparison of these alternative methods is sparse in the context of data generated via non-linear models where treatment effects are heterogeneous, such as is in the case of healthcare cost data. In this paper, we compare the performance of alternative regression and propensity score-based estimators in estimating average treatment effects on outcomes that are generated via non-linear models. Using simulations, we find that in moderate size samples (n= 5000), balancing on estimated propensity scores balances the covariate means across treatment arms but fails to balance higher-order moments and covariances amongst covariates, raising concern about its use in non-linear outcomes generating mechanisms. We also find that besides inverse-probability weighting (IPW) with propensity scores, no one estimator is consistent under all data generating mechanisms. The IPW estimator is itself prone to inconsistency due to misspecification of the model for estimating propensity scores. Even when it is consistent, the IPW estimator is usually extremely inefficient. Thus care should be taken before naively applying any one estimator to estimate ATE in these data. We develop a recommendation for an algorithm which may help applied researchers to arrive at the optimal estimator. We illustrate the application of this algorithm and also the performance of alternative methods in a cost dataset on breast cancer treatment.

Suggested Citation

Basu, Anirban and Polsky, Daniel and Manning, Willard G., Use of Propensity Scores in Non-Linear Response Models: The Case for Health Care Expenditures (June 2008). NBER Working Paper No. w14086. Available at SSRN: https://ssrn.com/abstract=1149332

Anirban Basu (Contact Author)

University of Chicago - Department of Medicine ( email )

5841 S. Maryland Ave
MC-2007
Chicago, IL 60637
United States
773 834 1796 (Phone)
773 834 2238 (Fax)

HOME PAGE: http://home.uchicago.edu/~abasu

Daniel Polsky

Bloomberg School of Public Health, Department of Health Policy and Management, Johns Hopkins University ( email )

624 North Broadway
Baltimore, MD 21205
United States

Johns Hopkins University - Carey Business School ( email )

100 International Drive
Baltimore, MD 21202
United States

Willard G. Manning

University of Chicago - Harris School of Public Policy ( email )

1155 East 60th Street
Chicago, IL 60637
United States
(773) 834-1971 (Phone)
(773) 702-1979 (Fax)

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
25
Abstract Views
697
PlumX Metrics