A Primer for Applying Propensity-Score Matching

The use of microeconometric techniques to estimate the effects of development policies has become a common approach not only for scholars, but also for policy-makers engaged in designing, implementing and evaluating projects in different fields. Among these techniques, Propensity-Score Matching (PSM) is increasingly applied in the policy evaluation community. This technical note provides a guide to the key aspects of implementing PSM methodology for an audience of practitioners interested in understanding its applicability to specific evaluation problems. The note summarizes the basic conditions under which PSM can be used to estimate the impact of a program and the data required. It explains how the Conditional Independence Assumption, combined with the Overlap Condition, reduces selection bias when participation in a program is determined by observable characteristics. It also describes different matching algorithms and some tests to assess the quality of the matching. Case studies are used throughout to illustrate important concepts in impact evaluation and PSM. In the annexes, the note provides an outline of the main technical aspects and a list of statistical and econometric software for implementing PSM.

[1]  J. Vernon,et al.  The Impact of Subsidized Health Insurance for the Poor: Evaluating the Colombian Experience Using Propensity Score Matching , 2005, International Journal of Health Care Finance and Economics.

[2]  P. Glemain.  L'intention de traiter , 2000 .

[3]  Alessandro Maffioli,et al.  Evaluating the Impact of Science, Technology and Innovation Programs: a Methodological Toolkit , 2011 .

[4]  G. Tabellini,et al.  Electoral Rules and Corruption , 2001, SSRN Electronic Journal.

[5]  Victor Lavy.  Evaluating the Effect of Teachers' Performance Incentives on Pupil Achievement , 2001 .

[6]  Sascha O. Becker,et al.  Estimation of Average Treatment Effects Based on Propensity Scores , 2002 .

[7]  M. Ravallion,et al.  Estimating the Benefit Incidence of an Antipoverty Program by Propensity-Score Matching , 2003 .

[8]  Sebastian Galiani,et al.  Water for Life: The Impact of the Privatization of Water Services on Child Mortality , 2004, Journal of Political Economy.

[9]  Stefano M. Iacus,et al.  Matching for Causal Inference Without Balance Checking , 2008 .

[10]  Marco Caliendo,et al.  Some Practical Guidance for the Implementation of Propensity Score Matching , 2005, SSRN Electronic Journal.

[11]  Petra Moser,et al.  How Do Patent Laws Influence Innovation? Evidence from Nineteenth-Century World Fairs , 2003 .

[12]  Petra E. Todd,et al.  Matching As An Econometric Evaluation Estimator , 1998 .

[13]  Jeffrey A. Smith,et al.  Does Matching Overcome Lalonde's Critique of Nonexperimental Estimators? , 2000 .

[14]  D. Rubin,et al.  The central role of the propensity score in observational studies for causal effects , 1983 .

[15]  G. Imbens,et al.  The Propensity Score with Continuous Treatments , 2005 .

[16]  G. Imbens,et al.  Implementing Matching Estimators for Average Treatment Effects in Stata , 2004 .

[17]  P. Holland.  Statistics and Causal Inference , 1985 .

[18]  D. Rubin,et al.  Constructing a Control Group Using Multivariate Matched Sampling Methods That Incorporate the Propensity Score , 1985 .

[19]  James E. Helmreich,et al.  PSAgraphics: An R Package to Support Propensity Score Analysis , 2009 .

[20]  G. Imbens,et al.  Large Sample Properties of Matching Estimators for Average Treatment Effects , 2004 .

[21]  Kosuke Imai,et al.  Causal Inference With General Treatment Regimes , 2004 .

[22]  G. Imbens,et al.  On the Failure of the Bootstrap for Matching Estimators , 2006 .

[23]  D. Czarnitzki,et al.  The Effects of Public R&D Subsidies on Firms' Innovation Activities , 2003 .

[24]  M. Lechner.  Program Heterogeneity and Propensity Score Matching: An Application to the Evaluation of Active Labor Market Policies , 2002, Review of Economics and Statistics.

[25]  D. Black,et al.  How robust is the evidence on the effects of college quality? Evidence from matching , 2004 .

[26]  Jorge M. Agüero,et al.  The Impact of Unconditional Cash Transfers on Nutrition : The South African Child , 2006 .

[27]  B. Sianesi,et al.  PSMATCH2: Stata module to perform full Mahalanobis and propensity score matching, common support graphing, and covariate imbalance testing , 2003 .

[28]  Alfonso Flores-Lagunes,et al.  Estimating the Effects of Length of Exposure to a Training Program: The Case of Job Corps , 2007, SSRN Electronic Journal.

[29]  M. Lechner.  The Effects of Enterprise-Related Training in East Germany on Individual Employment and Earnings , 1999 .