Advertisement

Journal für Betriebswirtschaft

, Volume 55, Issue 1, pp 37–62 | Cite as

Einsatzmöglichkeiten der Matching Methode zur Berücksichtigung von Selbstselektion

  • Sonja GenslerEmail author
  • Bernd Skiera
  • Martin Böhm
State-of-the-Art-Artikel

Zusammenfassung

Häufig ist es von Interesse, den Effekt der Teilnahme an einer Massnahme auf eine Ergebnisvariable zu untersuchen. Um jedoch eine Kausalität adäquat evaluieren zu können, müssen Selbstselektionseffekte berücksichtigt werden. Hierfür wird die Matching Methode vorgeschlagen. Bei der Matching Methode besteht das Ziel darin, durch die Bildung von Paaren von Teilnehmern und Nicht-Teilnehmern den Effekt der Teilnahme an einer Massnahme auf eine Ergebnisvariable zu bewerten. Dieser Beitrag stellt unterschiedliche Varianten der Matching Methode vor und vergleicht diese. Der Beitrag zeigt damit, wie bei betriebswirtschaftlichen Problemen Selbstselektionseffekte angemessen berücksichtigt werden können.

Schlüsselwörter

Selbstselektion Matching Methode Kausalität 

Abstract

In many situations it is of interest to determine the impact of a specific treatment on an outcome variable. In order to evaluate the causality between treatment and outcome variable, self-selection effects have to be taken into consideration. An approach to account for these self-selection effects is the matching method. The aim of the matching method is to evaluate the impact of a specific treatment on the outcome variable by building pairs of participants and non-participants of the treatment. This article illustrates and compares different specifications of the matching method and demonstrates how self-selection can be accounted for in managerial problems.

Keywords

Selection bias matching method causality 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literatur

  1. 1.
    Ashenfelter O (1978) Estimating the effect of training programs on earnings. Rev Econ Stat 60:47–57Google Scholar
  2. 2.
    Ashenfelter O, Rouse C (1998) Income, schooling, and ability: Evidence from a new sample of identical twins. Q J Econ: 253–284Google Scholar
  3. 3.
    Barabas J (2004) How deliberation affects policy opinions. Am Polit Sci Rev 98:1–16Google Scholar
  4. 4.
    Bjorklund A, Moffitt R (1987) The estimation of wage gains and welfare gains in self-selection models. Rev Econ Stat 69:42–49Google Scholar
  5. 5.
    Black DA, Smith J (2004) How robust is the evidence on the effects of college quality? Evidence from matching. J Econometrics 121:99–124Google Scholar
  6. 6.
    Boston Consulting Group (2001) The multichannel consumer – The need to integrate online and offline channels in Europe. BostonGoogle Scholar
  7. 7.
    Bortz J (1999) Statistik für Sozialwissenschaftler. Springer, Berlin Heidelberg New YorkGoogle Scholar
  8. 8.
    Bundesanstalt für Arbeit (2003) 138 Milliarden Euro für aktive Arbeitsmarktpolitik im Osten. Pressemitteilung vom 8. April 2003. http://www.soliserv.de/presse-arbeitsamt_2quartal-03.htm, abgerufen am 1. November 2004Google Scholar
  9. 9.
    Christensen B, Clement M, Albers S, Guldner S (2004) Zur Relevanz der Kontrollgruppenauswahl in der empirischen Forschung: Eine Analyse am Beispiel der Erfolgswirkung der Academy Awards im Filmgeschäft. Working paper, Christian-Albrechts-Universität zu KielGoogle Scholar
  10. 10.
    Cox D, Wermuth N (2004) Causality: A statistical view. Int Stat Rev 72:285–305Google Scholar
  11. 11.
    D’Agostino R (1998) Tutorial in biostatics: Propensity score methods for bias reduction in the comparison of a treatment to a non-randomized control group. Stat Med 17:2265–2281Google Scholar
  12. 12.
    Degeratu A, Rangaswamy A, Wu J (2000) Consumer choice behavior in online and traditional supermarkets: The effects of brand name, price and other search attributes. Int J Res Marketing 17:55–78Google Scholar
  13. 13.
    Dehejia RH, Wahba S (2002) Propensity score-matching methods for nonexperimental causal studies. Rev Econ Stat 84:151–161Google Scholar
  14. 14.
    Edwards D (2000) Introduction to graphical modelling. Springer, Berlin Heidelberg New YorkGoogle Scholar
  15. 15.
    Erdem T, Keane M, Sun B (1999) Missing price and coupon availability data in scanner panels: Correcting for the self-selection bias in the choice model parameters. J Econometrics 89:177–196Google Scholar
  16. 16.
    Fitzenberger B, Speckesser S (2003) Weiterbildungsmassnahmen in Ostdeutschland: Ein Misserfolg der Arbeitsmarktpolitik? In: Schmähl W (Hrsg) Wechselwirkungen zwischen Arbeitsmarkt und sozialer Sicherung (Soziale Sicherung und Arbeitsmarkt, Bd. 294). Duncker und Humblot, Berlin, S. 51–81Google Scholar
  17. 17.
    Granger C (1969) Investigating causal relations by econometric models and cross-spectral methods. Econometrica 37:424–438Google Scholar
  18. 18.
    Heckman J (1976) The common structure of statistical models of truncation, sample selection, and limited dependent variables and a simple estimator for such models. Ann Econ Soc Meas 5:475–492Google Scholar
  19. 19.
    Heckman J (1978) Dummy endogenous variables in a simultaneous equations system. Econometrica 46:931–960Google Scholar
  20. 20.
    Heckman J (1979) Sample selection bias as a specification error. Econometrica 47:152–162Google Scholar
  21. 21.
    Heckman J, Ichimura H, Smith J, Todd P (1996) Sources of selection bias in evaluating social programs: An interpretation of conventional measures and evidence on the effectiveness of matching as a program evaluation method. Proc Natl Acad Sci 93:13416–13420Google Scholar
  22. 22.
    Heckman J, Ichimura H, Smith J, Todd P (1998) Characterizing selection bias using experimantal data. Econometrica 66:1017–1098Google Scholar
  23. 23.
    Heckman J, Ichimura H, Todd P (1998) Matching as an econometric evaluation estimator. Rev Econ Stud 65:261–294Google Scholar
  24. 24.
    Heckman J, LaLonde R, Smith J (1999) The economics and econometrics of active labor market programs. In: Ashenfelter O, Card D (Hrsg) Handbook of Labor Economics, vol. III. Amsterdam, S. 1865–2097Google Scholar
  25. 25.
    Heckman J, Navarro-Lozano S (2004) Using matching, instrumental variables, and control functions to estimate economic choice models. Rev Econ Stat 86:30–57Google Scholar
  26. 26.
    Hitt LM, Frei FX (2002) Do better customers utilize electronic distribution channels? The case of PC banking. Manag Sci 48:732–748Google Scholar
  27. 27.
    Hujer R, Caliendo M, Radic D (2001) Nobody knows ... how do different evaluation estimators perform in a simulated labour market experiment? Working paper, Universität FrankfurtGoogle Scholar
  28. 28.
    Hujer R, Caliendo M, Radic D (2003) Methods and limitations of evaluation and impact research. Report on VET Research in Europe, CEDEFOP Project 0730. Working paper, Universität FrankfurtGoogle Scholar
  29. 29.
    Hujer R, Maurer K-O, Wellner M (1997) The impact of training on unemployment duration in West Germany – Combining a discrete hazard rate model with matching techniques. Working paper, Universität FrankfurtGoogle Scholar
  30. 30.
    Imbens G (2004) Nonparametric estimation of average treatment effects under exogeneity: A review. Rev Econ Stat 86:4–29Google Scholar
  31. 31.
    LaLonde R (1986) Evaluating the econometric evaluations of training programs with experimental data. Am Econ Rev 76:604–620Google Scholar
  32. 32.
    Lauritzen S (1999) Causal inference from graphical models. Research report R-99-2021, Aalborg University. http://www.math.aau.dk/research/reports/R-99-2021.ps, abgerufen am 7. Februar 2005Google Scholar
  33. 33.
    Lechner M (1998) Mikroökonomische Evaluationsstudien: Anmerkungen zu Theorie und Praxis. In: Pfeiffer F, Pohlmeier W (Hrsg) Qualifikation, Weiterbildung und Arbeitsmarkterfolg. Baden-Baden, S. 13–38Google Scholar
  34. 34.
    Lechner M (2002) Program heterogeneity and propensity score matching: An application to the evaluation of active labor market policies. Rev Econ Stat 84:205–220Google Scholar
  35. 35.
    Lee L-F (2000) Self-selection. In: Baltagi B (Hrsg) A companion to theoretical econometrics. Oxford, S. 384–409Google Scholar
  36. 36.
    Rässler S (2002) Statistical matching. Springer, Berlin Heidelberg New YorkGoogle Scholar
  37. 37.
    Rosenbaum P, Rubin D (1983) The central role of the propensity score in observational studies for causal effects. Biometrika 70:41–55Google Scholar
  38. 38.
    Rosenbaum P, Rubin D (1985) Constructing a control group using multivariate matched sampling methods that incorporate the propensity score. Am Stat 39:33–38Google Scholar
  39. 39.
    Roy A (1951) Some thoughts on the distribution of earnings. Oxford Econ Pap 3:135–145Google Scholar
  40. 40.
    Rubin D (1974) Estimating causal effects to treatments in randomised and nonrandomised studies. J Educational Psychol 66:688–701Google Scholar
  41. 41.
    Rubin D (1990) Comment on “Neyman (1923) and causal inference in experiments and observational studies”. Stat Sci 5:472–480Google Scholar
  42. 42.
    Singer B (1986) Self-selection and performance-based ratings: A case study in program evaluation. In: Wainer H (Hrsg) Drawing inference from self-selected samples. New York, S. 29–62Google Scholar
  43. 43.
    Smith J, Todd P (2000) Does matching overcome lalondes critique of nonexperimental estimators? Working paper, Penn Institute for Economic Research, PhiladelphiaGoogle Scholar
  44. 44.
    Wehrling R (2002) Retail E-banking: Tinkering pays off. ABA Banking J: 11–23Google Scholar
  45. 45.
    Wooldridge J (2003) Introductory econometrics – A modern approach. MasonGoogle Scholar
  46. 46.
    Zettelmeyer F, Morton FS, Silvia-Risso J (2001) Cowboys or cowards: Why are internet car prices lower? NBER working paper 8667. National Bureau of Economic Research, BerkeleyGoogle Scholar

Copyright information

© Wirtschaftsuniversität Wien, Austria 2005

Authors and Affiliations

  1. 1.Lehrstuhl für Betriebswirtschaftslehre, insbesondere Electronic CommerceJohann Wolfgang Goethe-Universität Frankfurt am MainFrankfurt am MainGermany

Personalised recommendations