Abstract
Summary Using criminal population conviction histories of recent offenders, prediction mod els are developed that predict three types of criminal recidivism: general recidivism, violent recidivism and sexual recidivism. The research question is whether prediction techniques from modern statistics, data mining and machine learning provide an improvement in predictive performance over classical statistical methods, namely logistic regression and linear discrim inant analysis. These models are compared on a large selection of performance measures. Results indicate that classical methods do equally well as or better than their modern counterparts. The predictive performance of the various techniques differs only slightly for general and violent recidivism, whereas differences are larger for sexual recidivism. For the general and violent recidivism data we present the results of logistic regression and for sexual recidivism of linear discriminant analysis.
Keywords
RecidivismLogistic regressionConvictionLinear discriminant analysisPsychologyStatisticsSex offensePopulationComputer sciencePoison controlMachine learningCriminologyHuman factors and ergonomicsDemographyMathematicsSexual abuseLawMedicineSociologyMedical emergency
Affiliated Institutions
Related Publications
All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously
Variable importance (VI) tools describe how much covariates contribute to a prediction model's accuracy. However, important variables for one well-performing model (for example,...
A working guide to boosted regression trees
1. Ecologists use statistical models for both explanation and prediction, and need techniques that are flexible enough to express typical features of their data, such as nonline...
Feature Engineering and Classifier Ensemble for KDD Cup 2010
KDD Cup 2010 is an educational data mining competition. Participants are asked to learn a model from students ’ past behavior and then predict their future performance. At Natio...
Interpretable Classification Models for Recidivism Prediction
Summary We investigate a long-debated question, which is how to create predictive models of recidivism that are sufficiently accurate, transparent and interpretable to use for d...
Multiple Regression in Behavioral Research: Explanation and Prediction
Part I: Foundations of Multiple Regression Analysis. Overview. Simple Linear Regression and Correlation. Regression Diagnostics. Computers and Computer Programs. Elements of Mul...
Publication Info
- Year
- 2012
- Type
- article
- Volume
- 176
- Issue
- 2
- Pages
- 565-584
- Citations
- 123
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
123
OpenAlex
Cite This
Nikolaj Tollenaar,
P.G.M. van der Heijden
(2012).
Which Method Predicts Recidivism Best?: A Comparison of Statistical, Machine Learning and Data Mining Predictive Models.
Journal of the Royal Statistical Society Series A (Statistics in Society)
, 176
(2)
, 565-584.
https://doi.org/10.1111/j.1467-985x.2012.01056.x
Identifiers
- DOI
- 10.1111/j.1467-985x.2012.01056.x