About | HeinOnline Law Journal Library | HeinOnline Law Journal Library | HeinOnline

LOG IN
LOG IN


11 Crim. Just. & Behavior 3 (1984)

handle is hein.journals/crmjusbhv11 and id is 1 raw text is: THE CLINICAL AND STATISTICAL PREDICTION OF RECIDIVISM J. STEPHEN WORMITH COLIN S. GOLDSTONE Regional Psychiatric Centre, Saskatoon, and University of Saskatchewan The purpose of this research series was to investigate characteristics of a previously devised Recidivism Prediction Scheme with a regional sample of offenders and to assess possible means of integrating clinical and actuarial data sets. Study I revealed high interrater reliability coefficients, although agreement varied by items. Natives, maximum security inmates, and property offenders received poor prognostic scores in Studies 1 and 2. Study 2 provided validity data on the instrument and suggested how clinical and statistically based decisions might be integrated. However, in Study 3, the incorporation of clinical data into an actuarial scheme did little to improve the predictive accuracy of both multiple regression and unit weight systems when they were subjected to cross-validation. T he prediction of criminal recidivism among cohorts of incarcerated offenders has a long and varied history. The first crude attempts were pioneered by Hart (1923) and Burgess (1928), who developed experience tables in which recidivism rates were listed for various offender groups. Since then, the development of computers and large data sets has led to sophisticated prediction schemes based on large and Authors' Note: The authors wish to thank the National Parole Board (Prairie Region) and the staff of the Parole Board office for their cooperation and assistance. These studies were supported in part by the CRIMINAL JUSTICE AND BEHAVIOR, Vol. 11 No. 1, March 1984 3-34 © 1984 American Association of Correctional Psychologists 3 from the SAGE Social Science Collections. All Rights Reserved.