References (39)


Citations (4)



Propensity Score Matching and Variations on the Balancing Test

Wang-Sheng Lee

Deakin University

August 11, 2006

This paper focuses on the role of balancing tests when employing propensity score matching methods. The idea behind these tests are to check to see if observations with the same propensity score have the same distribution of observable covariates independent of treatment status. Currently, multiple versions of the balancing test exist in the literature. One troubling aspect is that different balancing tests sometimes yield different answers. This paper highlights the importance of distinguishing between balancing tests that are conducted before matching and after matching, and provides a Monte Carlo examination of four commonly employed balancing tests. We highlight the poor size properties of these commonly employed balancing tests and demonstrate how non-parametric versions of before and after matching tests provide much better test sizes. Finally, we illustrate how balancing tests are of little utility if the conditional independence assumption underlying matching estimators is not fulfilled.

Number of Pages in PDF File: 48

Keywords: Matching, Propensity score, Monte Carlo simulation

JEL Classification: C21

Open PDF in Browser Download This Paper

Date posted: October 19, 2006  

Suggested Citation

Lee, Wang-Sheng, Propensity Score Matching and Variations on the Balancing Test (August 11, 2006). Available at SSRN: http://ssrn.com/abstract=936782 or http://dx.doi.org/10.2139/ssrn.936782

Contact Information

Wang-Sheng Lee (Contact Author)
Deakin University ( email )
Burwood, Victoria 3215
+61392446669 (Phone)
HOME PAGE: http://www.deakin.edu.au/buslaw/aef/staff/profiles/lee.php
Feedback to SSRN

Paper statistics
Abstract Views: 1,936
Downloads: 412
Download Rank: 46,207
References:  39
Citations:  4

© 2015 Social Science Electronic Publishing, Inc. All Rights Reserved.  FAQ   Terms of Use   Privacy Policy   Copyright   Contact Us
This page was processed by apollo6 in 0.375 seconds