Predicting Risk at Sentencing: Occurrence and Timing of Re-Arrest Among Serious Offenders

• In Event: Strategies for Managing Risk within the Legal System

Abstract

Judges would benefit from having systematic information on the likelihood of recidivism when making sentencing decisions. This study identifies risk factors of 10,002 serious (level 5) offenders sentenced and released in Pennsylvania. Focusing on information judges have at sentencing, this study analyzes the relationship between offender and case characteristics and likelihood of recidivism over the course of 11.5 years. Survival analysis and Cox Proportional Hazards models are used to identify significant covariate patterns among convicted individuals with a new arrest or parole revocation, and Area Under the Curve (AUC) estimates are used to compare the predictive power using two cross-validation samples and a test sample. This research informs efforts to develop a risk assessment instrument by identifying ten case and offender characteristics that consistently and significantly predict recidivism.

Authors

• Julia Laskorunsky, Pennsylvania State University

• Matthew DeMichele, RTI International