Encyclopedia of Criminology and Criminal Justice

2014 Edition
| Editors: Gerben Bruinsma, David Weisburd

Propensity Score Matching

Reference work entry
DOI: https://doi.org/10.1007/978-1-4614-5690-2_46


Multivariate regression-based methods dominate the research literature in criminology for estimating the effects of causal variables. As many scholars have noted, however, regression suffers from a number of methodological and practical limitations (Berk 2004). On its own, regression provides a poor analytic framework for conceptualizing causal inference, offers limited tools to address nonlinear relationships, and encourages researchers to cherry-pick models in a manner that may bias the results of a study. Despite these issues, criminologists have failed to take full advantage of other approaches to observational research developed in the fields of statistics and biostatistics.

One alternative is propensity score matching (Rosenbaum and Rubin 1983), an analytic method closely associated with the Rubin Causal Model (RCM; Rubin 2008; Holland 1986). Though a number of criminological studies have used propensity score approaches (e.g., Haviland et al. 2007; MacDonald et al. 2007...

This is a preview of subscription content, log in to check access.



The data used in this case study were originally collected as part of a grant funded by the National Institute on Drug Abuse (NIDA) (grant R01DA16722) to Andrew Morral at the RAND Corporation. The opinions expressed in this entry are those of the authors and do not represent the official positions of NIDA or the RAND Corporation.

Recommended Reading and References

  1. Berk RA (2004) Regression analysis: a constructive critique. Sage, Thousand OaksGoogle Scholar
  2. Berk RA, Newton PJ (1985) Does arrest really deter wife battery? An effort to replicate the findings of the Minneapolis spouse abuse experiment. Am Sociol Rev 50:253–262Google Scholar
  3. Berk RA, Rauma D (1983) Capitalizing on nonrandom assignment to treatments: a regression-discontinuity evaluation of a crime-control program. J Am Stat Assoc 78:21–27Google Scholar
  4. Berk RA, Li A, Hickman L (2005) Statistical difficulties in determining the role of race in capital cases: a re-analysis of data from the state of Maryland. J Quant Criminol 21:365–390Google Scholar
  5. Bertsekas DP (1981) A new algorithm for the assignment problem. Math Program 21:152–171Google Scholar
  6. Blalock H (1964) Causal inference in nonexperimental research. University of North Carolina Press, Chapel HillGoogle Scholar
  7. Campbell D, Stanley J (1963) Experimental and quasi-experimental designs for research and teaching. In: Gage NL (ed) Handbook of research on teaching. Rand McNally, ChicagoGoogle Scholar
  8. Cochran W, Cox G (1950) Experimental designs. Wiley, New YorkGoogle Scholar
  9. Cochran WG, Rubin DB (1973) Controlling bias in observational studies. Sankhya Indian J Stat 35:417–446Google Scholar
  10. Cochran W (1983) Planning and analysis of observational studies. Wiley, New YorkGoogle Scholar
  11. Cornfield J, Haenszel W, Hammond E, Lilienfeld A, Shimkin M, Wynder E (1959) Smoking and lung cancer: recent evidence and a discussion of some questions. J Natl Cancer Inst 22:173–203Google Scholar
  12. Fisher R (1935) The design of experiments. Oliver and Boyd, EdinburghGoogle Scholar
  13. Freedman DA, Berk RA (2008) Weighting regressions by propensity scores. Eval Rev 32:392–409Google Scholar
  14. Greiner JD (2008) Causal inference in civil rights litigation. Harv Law Rev 122:533–598Google Scholar
  15. Hansen BB, Klopfer SO (2006) Optimal full matching and related designs via network flows. J Comput Graphical Statist 15: 609–627Google Scholar
  16. Haviland A, Nagin DS, Rosenbaum PR (2007) Combining propensity score matching and group-based trajectory analysis in an observational study. Psychol Methods 12:247–267Google Scholar
  17. Hirano K, Imbens GW (2001) Estimation of causal effects using propensity score weighting: an application to data on right heart catheterization. Health Serv Outcomes Res Methodol 2:259–278Google Scholar
  18. Hirano K, Imbens GW (2004) The propensity score with continuous treatments. In: Gelman A, Meng XL (eds) Applied Bayesian modeling and causal inference from incomplete-data perspectives. Wiley InterScience, West Sussex, pp 73–84Google Scholar
  19. Holland P (1986) Statistics and causal inference. J Am Stat Assoc 81:945–960Google Scholar
  20. Hollander M, Wolfe DA (1999) Nonparametric statistics methods, 2nd edn. Wiley, New YorkGoogle Scholar
  21. Joffee MM, Rosenbaum PR (1999) Invited commentary: propensity scores. Am J Epidemiol 150:327–333Google Scholar
  22. Lehmann EL (1998) Nonparametrics: statistical methods based on ranks. Prentice Hall, Saddle RiverGoogle Scholar
  23. MacDonald JM, Stokes R, Ridgeway G, Riley KJ (2007) Race, neighborhood context, and perceptions of injustice by the Police in Cincinnati. Urban Studies 44:2567–2585Google Scholar
  24. McCaffrey DF, Ridgeway G, Morral AR (2004) Propensity score estimation with boosted regression for evaluating causal effects in observational studies. Psychol Methods 9:403–425Google Scholar
  25. Morral AR, McCaffrey DF, Ridgeway G (2004) Effectiveness of community-based treatment for substance-abusing adolescents: 12-month outcomes of youths entering phoenix academy or alternative probation dispositions. Psychol Addict Behav 18:257–268Google Scholar
  26. Paternoster R, Brame R (2008) Reassessing race disparities in Maryland capital cases. Criminology 46(4):971–1008Google Scholar
  27. Rosenbaum P, Rubin D (1983) The central role of the propensity score in observational studies for causal effects. Biometrika 70:41–55Google Scholar
  28. Rosenbaum P, Rubin D (1985) Constructing a control group using multivariate matched sampling incorporating the propensity core. Amer Statist 39:33–38Google Scholar
  29. Rosenbaum PR (2002) Observational studies. Springer, New YorkGoogle Scholar
  30. Rosenbaum P (2009) Design of observational studies. Springer, New YorkGoogle Scholar
  31. Rosenbaum PR (2010) Design of observational studies. Springer, New YorkGoogle Scholar
  32. Rubin DB (1974) Estimating causal effects of treatments in randomized and nonrandomized studies. J Educ Psychol 66(5):688–701Google Scholar
  33. Rubin DB (2008) For objective causal inference, design trumps analysis. Ann Appl Stat 2:808–840Google Scholar
  34. Sampson R (2010) Gold standard myths: observations on the experimental turn in quantitative criminology. J Quant Crim 26:489–500Google Scholar
  35. Westreich D, Lessler J, Funk MJ (2010) Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression. J Clin Epidemiol 63:826–833Google Scholar
  36. Zuberi T (2001) Thicker than blood: how racial statistics lie. University of Minnesota Press, MinneapolisGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  1. 1.Department of CriminologyUniversity of PennsylvaniaPhiladelphiaUSA