Svenska To intranet

Covariate selection for non-parametric estimation of treatment effects

Author: Xavier de Luna, And Ingeborg Waernbaum, And

Summary of Working paper 2005:4

In observational studies, the non-parametric estimation of a binary treatment
effect is often performed by matching each treated individual with a control
unit which is similar in observed characteristics (covariates). In practical
applications, the reservoir of covariates available may be extensive and the question
arises which covariates should be matched for. The current practice consists
in matching for covariates which are not balanced for the treated and the control
groups, i.e. covariates affecting the treatment assignment. This paper develops
a theory based on graphical models, whose results emphasize the need for
methods looking both at how the covariates affect the treatment assignment
and the outcome. Furthermore, we propose identification algorithms to select
a minimal set of covariates to match for. An application to the estimation of
the effect of a social program is used to illustrate the implementation of such
algorithms.
Keywords: Graphical models, Matching estimators, Observational studies,
Potential outcomes, Social programs.
JEL: C14


In observational studies, the non-parametric estimation of a binary treatment effect is often performed by matching each treated individual with a control unit which is similar in observed characteristics (covariates). In practical applications, the reservoir of covariates available may be extensive and the question arises which covariates should be matched for. The current practice consists in matching for covariates which are not balanced for the treated and the control groups, i.e. covariates affecting the treatment assignment. This paper develops a theory based on graphical models, whose results emphasize the need for methods looking both at how the covariates affect the treatment assignment and the outcome. Furthermore, we propose identification algorithms to select a minimal set of covariates to match for. An application to the estimation of the effect of a social program is used to illustrate the implementation of such algorithms.

Keywords: Graphical models, Matching estimators, Observational studies, Potential outcomes, Social programs.
JEL: C14

Research areas