Randomized experiments in criminology: What have we learned in the last two decades?

This paper aims to review randomized experiments in criminology with offending outcomes and reasonably large numbers that were published between 1982 and 2004. A total of 83 experiments are summarized, compared with only 35 published between 1957 and 1981: 12 on policing, 13 on prevention, 14 on corrections, 22 on courts, and 22 on community interventions. Randomized experiments are still relatively uncommon, but there have been more large-scale multi-site experiments and replication programs. There have also been several experiments in which 100 or more places were randomly assigned. Relatively few experiments (only 10 out of 83) were conducted outside the United States. Meta-analyses suggest that prevention methods, correctional therapy, batterer programs, drug courts, juvenile restitution and deterrent policing were effective in reducing offending, while Scared Straight and boot camp programs caused a significant increase in offending.     

A contribution to the discussion of probabilities and human hair comparisons

The paper by Gaudette and Keeping on "An Attempt at Determining Probabilities in Human Scalp Hair Comparison" in the Journal of Forensic Sciences (Vol. 19, No. 3, July 1974, pp. 599-606) has provoked considerable controversy. This paper highlights two of the sources of the controversy and shows how the probability, 1/4500, quoted by Gaudette and Keeping should be treated with caution. The necessity of the use of a likelihood ratio statistic is described. It is suggested that the hair examination form resulting from the responses to the questionnaire recently distributed by the authors and also the discussions at Quantico (Proceedings of the International Symposium on Forensic Hair Comparisons, 25-27 June 1985, Quantico VA) should be used to facilitate the collection of the data which will be necessary to enable a likelihood ratio statistic to be estimated effectively.