Journal of Quantitative Criminology

, Volume 4, Issue 3, pp 209–223

When random assignment fails: Some lessons from the Minneapolis Spouse Abuse Experiment

Authors

  • Richard A. Berk
    • Department of Sociology and Program in Social StatisticsHaines Hall, University of California
  • Gordon K. Smyth
    • Statistics and Applied Probability ProgramUniversity of California, Santa Barbara
  • Lawrence W. Sherman
    • Department of Criminal JusticeUniversity of Maryland
Article

DOI: 10.1007/BF01072450

Cite this article as:
Berk, R.A., Smyth, G.K. & Sherman, L.W. J Quant Criminol (1988) 4: 209. doi:10.1007/BF01072450

Abstract

In this paper, we consider what may be done when researchers anticipate that in the implementation of field experiments, random assignment to experimental and control groups is likely to be flawed. We then reanalyze data from the Minneapolis Spouse Abuse Experiment in a manner that explicitly models violations of random assignment. As anticipated, we find far larger treatment effects than previously reported. The techniques developed should be useful in a wide variety of settings when random assignment is implemented imperfectly.

Key words

field experiments random assignment domestic violence selection bias

Copyright information

© Plenum Publishing Corporation 1988