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

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.