SOME PRACTICAL GUIDANCE FOR THE IMPLEMENTATION OF PROPENSITY SCORE MATCHING

Journal of Economic Surveys - Tập 22 Số 1 - Trang 31-72 - 2008
Marco Caliendo1, Sabine Kopeinig2
1IZA, Bonn
2UNIVERSITY OF COLOGNE

Tóm tắt

Abstract Propensity score matching (PSM) has become a popular approach to estimate causal treatment effects. It is widely applied when evaluating labour market policies, but empirical examples can be found in very diverse fields of study. Once the researcher has decided to use PSM, he is confronted with a lot of questions regarding its implementation. To begin with, a first decision has to be made concerning the estimation of the propensity score. Following that one has to decide which matching algorithm to choose and determine the region of common support. Subsequently, the matching quality has to be assessed and treatment effects and their standard errors have to be estimated. Furthermore, questions like ‘what to do if there is choice‐based sampling?’ or ‘when to measure effects?’ can be important in empirical studies. Finally, one might also want to test the sensitivity of estimated treatment effects with respect to unobserved heterogeneity or failure of the common support condition. Each implementation step involves a lot of decisions and different approaches can be thought of. The aim of this paper is to discuss these implementation issues and give some guidance to researchers who want to use PSM for evaluation purposes.

Từ khóa


Tài liệu tham khảo

10.1111/1468-0084.00211

10.1016/S0304-4076(02)00201-4

10.1111/0034-6527.00321

10.1111/j.1468-0262.2006.00655.x

Abadie A.andImbens G.(2006b)On the failure of the bootstrap for matching estimators. Working Paper Harvard University .

10.1177/1536867X0400400307

10.1162/003465304323023679

10.1002/jae.919

Augurzky B.andSchmidt C.(2001)The propensity score: a means to an end. Discussion Paper No. 271 IZA.

Becker S.O., 1964, Human Capital

10.1177/1536867X0200200403

10.1177/1536867X0700700104

Bergemann A. Fitzenberger B.andSpeckesser S.(2001)Evaluating the employment effects of public sector sponsored training in East Germany: conditional difference‐in‐differences and Ashenfelters' dip. Discussion Paper University of Mannheim.

10.1016/j.jeconom.2003.10.006

10.1111/j.1475-5890.2000.tb00031.x

10.1007/s10258-002-0010-3

10.1111/j.1467-985X.2004.00360.x

10.1016/j.ssresearch.2005.06.006

Breiman L., 1984, Classification and Regression Trees

10.1007/978-3-642-57615-7_5

10.1257/jep.15.4.129

Bryson A.(2002)The union membership wage premium: an analysis using propensity score matching. Discussion Paper No. 530 Centre for Economic Performance London .

Bryson A. Dorsett R.andPurdon S.(2002)The use of propensity score matching in the evaluation of labour market policies. Working Paper No. 4 Department for Work and Pensions.

10.1007/s10182-006-0230-4

Caliendo M., 2007, The employment effects of job creation schemes in Germany – a microeconometric evaluation, Advances in Econometrics

10.2307/2528036

Crump R. Hotz V. Imbens G.andMitnik O.(2005)Moving the goalposts: addressing limited overlap in estimation of average treatment effects by changing the estimand. Working Paper University of California at Berkeley .

Davies R.andKim S.(2003)Matching and the estimated impact of interlisting. Discussion Paper in Finance No. 2001‐11 ISMA Centre Reading .

10.1016/j.jeconom.2004.04.012

10.1080/01621459.1999.10473858

10.1162/003465302317331982

10.1257/jep.15.4.11

10.1111/j.0081-1750.2004.00154.x

Fredriksson P.andJohansson P.(2004)Dynamic treatment assignment – the consequences for evaluations using observational data. Discussion Paper No. 1062 IZA.

Galdo J.(2004)Evaluating the performance of non‐experimental estimators: evidence from a randomized UI program. Working Paper Centre for Policy Research Toronto .

10.1111/1468-0297.00072

Greene W.H., 2003, Econometric Analysis

10.2307/1390693

10.2307/2998560

Ham J. Li X.andReagan P.(2004)Propensity score matching a distance‐based measure of migration and the wage growth of young men. Working Paper Department of Economics Ohio State University .

10.2307/146178

Heckman J., 1985, Longitudinal Analysis of Labor Market Data, 156, 10.1017/CCOL0521304539.004

10.1111/1468-0297.00451

Heckman J.andTodd P.(2004)A note on adapting propensity score matching and selection models to choice based samples. Working Paper first draft 1995 this draft Nov. 2004 University of Chicago .

10.2307/2971733

10.2307/2971729

10.2307/2999630

10.1111/1467-937X.00044

10.1016/S1573-4463(99)03012-6

Hirano K., 2002, Estimation of causal effects using propensity score weighting: an application to data on right heart catherization, Health Services and Outcomes Research Methodology, 2, 259

10.1111/1468-0262.00442

10.1287/mnsc.48.6.732.188

10.1080/01621459.1986.10478354

Ichino A. Mealli F.andNannicini T.(2006)From temporary help jobs to permanent employment: what can we learn from matching estimators and their sensitivity. Discussion Paper No. 2149 IZA Bonn .

10.1093/biomet/87.3.706

10.1257/000282803321946921

10.1162/003465304323023651

Lechner M., 1998, Qualifikation, Weiterbildung und Arbeitsmarkterfolg. ZEW‐Wirtschaftsanalysen Band 31

10.2307/1392240

10.2307/146329

Lechner M., 2001, Econometric Evaluation of Labour Market Policies, 1, 10.1007/978-3-642-57615-7

Lechner M.(2001b)A note on the common support problem in applied evaluation studies. Discussion Paper No. 2001‐01 University of St Gallen SIAW .

10.1111/1467-985X.0asp2

Lechner M.(2004)Sequential matching estimation of dynamic causal models. Discussion Paper No. 1042 IZA.

Lechner M.andMiquel R.(2005)Identification of the effects of dyanmic treatments by sequential conditional independence assumptions. Working Paper SIAW.

Leuven E.andSianesi B.(2003)PSMATCH2: Stata module to perform full Mahalanobis and propensity score matching common support graphing and covariate imbalance testing. Software http://ideas.repec.org/c/boc/bocode/s432001.html.

Navarro‐Lozano S.(2002)Matching selection and the propensity score: evidence from training in Mexico. Working Paper University of Chicago .

10.1017/CBO9780511612503

10.1002/(SICI)1099-1557(200003/04)9:2<93::AID-PDS474>3.0.CO;2-I

10.1007/978-1-4757-3692-2

10.1111/j.2517-6161.1983.tb01242.x

10.1093/biomet/70.1.41

10.1080/01621459.1984.10478078

10.2307/2683903

10.1093/oxfordjournals.oep.a041827

10.2307/2529685

10.1037/h0037350

10.2307/2286330

10.2307/2287653

10.2307/2533160

Sianesi B.(2001)An evaluation of the active labour market programmes in Sweden. Working Paper No. 2001:5 IFAU – Office of Labour Market Policy Evaluation.

10.1162/003465304323023723

10.1007/978-1-4899-3324-9

10.1111/1467-9531.271030

Smith J., 2000, A critical survey of empirical methods for evaluating active labor market policies, Schweizerische Zeitschrift fuer Volkswirtschaft und Statistik, 136, 1

10.1016/j.jeconom.2004.04.011

Wooldridge J.M., 2004, Econometric Analysis of Cross Section and Panel Data

Zhao Z.(2000)Data issues of using matching methods to estimate treatment effects: an illustration with NSW data set. Working Paper China Centre for Economic Research.

10.1162/003465304323023705