Using multiple performance metrics and measures of recidivism on 40,740 Minnesota offenders released from prison between 2006 and 2011, this study evaluated the performance of prediction models developed with both Burgess methodology and supervised learning algorithms (i.e., statistical and machine learning algorithms).
Recent studies have compared the performance of machine learning algorithms versus logistic regression models in predicting recidivism. Existing research, however, has not compared their performance to Burgess methodologya transparent, simplistic and summative classification technique used to develop some of the most widely used risk and needs assessment instruments currently used in corrections. The results of the current study show that, compared to the best supervised learning classifiers, use of Burgess methodology yielded inferior performance in terms of predictive discrimination, accuracy, and calibration. (Publisher abstract modified)
Downloads
Related Datasets
Similar Publications
- Comparative Evaluation of Genotyping Technologies for Investigative Genetic Genealogy in Sexual Assault Casework
- Longitudinal Cohort Study: Predictive Validity of the Structured Assessment of Violence Risk in Youth Individual/Clinical Risk Factor on Recidivism Among Mississippi Justice-Involved Youth
- The Ties That Bind: The Association Between Social Network Ties, Integration, and Stress Among Incarcerated Women