A New Non-Parametric Matching Method for Covariate Adjustment with Application to Economic Evaluation

31 Pages Posted: 15 Nov 2008 Last revised: 30 Jun 2009

See all articles by Jasjeet S. Sekhon

Jasjeet S. Sekhon

UC Berkeley

Richard Grieve

London School of Hygiene and Tropical Medicine

Date Written: June 30, 2009

Abstract

In health economic studies that use observational data, a key concern is how to adjust for imbalances in baseline covariates due to the non-random assignment of the programs under evaluation. Traditional methods of covariate adjustment such as regression and propensity score matching are model dependent and often fail to replicate theresults of randomized controlled trials. We demonstrate a new non-parametric matching method, Genetic Matching, which is a generalization of propensity score and Mahalanobis distance matching (Sekhon forthcoming), using two contrasting case studies. In the first, an economic evaluation of a clinical intervention (Pulmonary Artery Catheterization), applying Genetic Matching to observational data replicates the substantive results of a corresponding randomized controlled trial unlike the extant literature. And in the second case study evaluating capitation versus fee-for-service, Genetic Matching radically improves balance on baseline covariates and overturns previous conclusions based on traditional methods.

JEL Classification: C90

Suggested Citation

Sekhon, Jasjeet S. and Grieve, Richard, A New Non-Parametric Matching Method for Covariate Adjustment with Application to Economic Evaluation (June 30, 2009). Experiments in Political Science 2008 Conference Paper. Available at SSRN: https://ssrn.com/abstract=1301767 or http://dx.doi.org/10.2139/ssrn.1301767

Jasjeet S. Sekhon (Contact Author)

UC Berkeley ( email )

310 Barrows Hall
Berkeley, CA 94720
United States

Richard Grieve

London School of Hygiene and Tropical Medicine ( email )

Keppel Street
London, WC1E 7HT
United Kingdom

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
95
Abstract Views
986
rank
284,885
PlumX Metrics