PREDICTING REARREST FOR VIOLENCE AMONG SERIOUS YOUTHFUL OFFENDERS

This article presents the results of an analysis of the risk of arrest for a violent crime for a cohort of youthful parolees. The sample consists of 1,949 individuals paroled by the California Youth Authority between July 1, 1981, and June 30, 1982. Results of a multivariate competing hazards analysis suggest that prior criminal history and socioeconomic variables are powerful predictors of both the timing and the charge of first arrest following parole. In comparison to results from a model predicting rearrest for any crime, rearrest for violence is significantly influenced by prior arrests for violence and several family pathology variables, including evidence of family violence and parental criminality. Prior gang involvement and heavy use of alcohol and illicit drugs have little predictive ability for violent recidivism among our sample. The results indicate that prediction of rearrest for violence among a group of serious youthful offenders may be practical if criminal history, institutional behavior, and personal background characteristics are all taken into account.