Prediction Of Criminal Recidivism Research Articles

Clients' current presentation yields best prediction of criminal recidivism: Jointly modeling repeated assessments of risk and recidivism outcomes in a community sample of paroled New Zealanders.

Clinicians often rely on readily observable intermediate outcomes (e.g., symptoms) to assess the likelihood of events that occur outside of treatment (e.g., relapse). Similarly, those monitoring clients with histories of criminal involvement attempt to prevent adverse outcomes considered likely and intervene when symptoms/risk factors fluctuate. Our aim was to develop a stronger understanding of associations between evolving symptoms/risk factors and case outcomes, yielding clearer practice implications. We used longitudinal, multiple reassessment risk data from 3,421 individuals paroled in New Zealand. We used joint modeling to test the association between individual trajectories of psychosocial risk factor scores, assessed using Dynamic Risk Assessment for Offender Re-entry, and recidivism (official records of parole violations or criminal charges resulting in reconviction). We examined whether recent clinically relevant features of risk presentation (e.g., current levels, recent rate of change) predicted recidivism better than the entirety of the risk assessment trajectory. Although each model demonstrated similar predictive validity, measures of model fit indicated that models using current trajectory features outperformed those using the entire assessment history to predict recidivism. Change in dynamic risk factors is consistently associated with recidivism outcomes. When using changeable factors to monitor clients' current risk for recidivism, practitioners should focus on current presentation rather than the entire assessment history, although differences in predictive discrimination are small. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Supplemental Material for Clients’ Current Presentation Yields Best Prediction of Criminal Recidivism: Jointly Modeling Repeated Assessments of Risk and Recidivism Outcomes in a Community Sample of Paroled New Zealanders

Supplemental Material for Clients’ Current Presentation Yields Best Prediction of Criminal Recidivism: Jointly Modeling Repeated Assessments of Risk and Recidivism Outcomes in a Community Sample of Paroled New Zealanders

The Application of Machine Learning to a General Risk–Need Assessment Instrument in the Prediction of Criminal Recidivism

The Level of Service/Case Management Inventory (LS/CMI) is one of the most frequently used tools to assess criminogenic risk–need in justice-involved individuals. Meta-analytic research demonstrates strong predictive accuracy for various recidivism outcomes. In this exploratory study, we applied machine learning (ML) algorithms (decision trees, random forests, and support vector machines) to a data set with nearly 100,000 LS/CMI administrations to provincial corrections clientele in Ontario, Canada, and approximately 3 years follow-up. The overall accuracies and areas under the receiver operating characteristic curve (AUCs) were comparable, although ML outperformed LS/CMI in terms of predictive accuracy for the middle scores where it is hardest to predict the recidivism outcome. Moreover, ML improved the AUCs for individual scores to near 0.60, from 0.50 for the LS/CMI, indicating that ML also improves the ability to rank individuals according to their probability of recidivating. Potential considerations, applications, and future directions are discussed.

Supplemental Material for Reassessment Improves Prediction of Criminal Recidivism: A Prospective Study of 3,421 Individuals in New Zealand

Supplemental Material for Reassessment Improves Prediction of Criminal Recidivism: A Prospective Study of 3,421 Individuals in New Zealand

The prediction of criminal recidivism in male juvenile delinquents

Previous studies have demonstrated a strong association of criminal behavior of juvenile delinquents with delinquents? personality traits and family interactions. However, little is known about the extent to which family interactions and personality traits are associated with criminal recidivism. The present study aimed to examine these relationships, using the Velikih pet plus dva (Big Five Plus Two) ? short version (assessing Neuroticism, Extraversion, Openness to experience, Conscientiousness, Aggressiveness, Positive Valence, Negative Valence), The Quality of Family Interaction Scale (Satisfaction with family, Mother and Father Acceptance/Rejection), and official data from criminal records. The study included 61 institutionalized delinquents and 64 non-delinquents, 15 to 18 years of age. Neuroticism, Openness to experience, Conscientiousness, Negative valence, acceptance by father and rejection by mother are statistically significant predictors of criminal recidivism in juvenile delinquents. Delinquents showed higher Neuroticism, lower Conscientiousness and acceptance by mother compared to non-delinquents.

The prediction of criminal recidivism using routinely available file information

Objective. The aim of the present study was to cross-validate the investigation of Buchanan and Leese (2006) into the prediction of criminal recidivism. Method. The sample comprised offenders in the criminal justice system of the Canton of Zürich – Switzerland, who were discharged to the community. Participants were followed, and evidence of subsequent charges and convictions for both general and serious recidivism was investigated at fixed periods of 2.5, 6.5, and 10.5 years. The predictive validity of socio-demographic, criminal history, and legal class information was assessed using logistic regression as well as log-likelihood, receiver operating characteristic curve, and contingency analyses. Results. A multivariable model including age and criminal history information was found to produce the highest rates of predictive validity for general and serious recidivism. Conclusion. Information regularly accessible in forensic practice may be able to guide clinicians as to the recidivism risk level of their patients.

Are the Major Risk/Need Factors Predictive of Both Female and Male Reoffending?

The Level of Service/Case Management Inventory (LS/CMI) and the Youth version (YLS/CMI) generate an assessment of risk/need across eight domains that are considered to be relevant for girls and boys and for women and men. Aggregated across five data sets, the predictive validity of each of the eight domains was gender-neutral. The composite total score (LS/CMI total risk/need) was strongly associated with the recidivism of males (mean r = .39, mean AUC = .746) and very strongly associated with the recidivism of females (mean r = .53, mean AUC = .827). The enhanced validity of LS total risk/need with females was traced to the exceptional validity of Substance Abuse with females. The intra-data set conclusions survived the introduction of two very large samples composed of female offenders exclusively. Finally, the mean incremental contributions of gender and the gender-by-risk level interactions in the prediction of criminal recidivism were minimal compared to the relatively strong validity of the LS/CMI risk level. Although the variance explained by gender was minimal and although high-risk cases were high-risk cases regardless of gender, the recidivism rates of lower risk females were lower than the recidivism rates of lower risk males, suggesting possible implications for test interpretation and policy.

Underreporting of crime-related content and the prediction of criminal recidivism among violent offenders.

Underreporting of crime-related content and the prediction of criminal recidivism among violent offenders.

The prediction of criminal recidivism

Instruments based on actuarial forensic risk assessment models are sensitive to the calibration sample, and the inclusion criteria for the subjects of a study population will influence the features of the resulting model. If the same instrument is used in populations that are not part of the calibration sample, the discriminative validity of the instrument is jeopardized; thus the definition of the calibration sample is very important. The aim of this study was to examine how sensitive prognostic models are to the calibration sample. Two samples (N = 773) of offenders sentenced to at least 10 months in prison for a violent or sexual offense were used in this study. The "sanction sample" (recruited during August 2000, N = 515) consisted of all violent and sexual offenders actively administrated by the Criminal Justice System of Zurich, Switzerland. The "verdict sample" (recruited over two years, N = 258) included all offenders convicted in the Canton of Zurich during a two-year period. Both samples were unbiased, since all subjects that met the study criteria were included. In the first analysis, differences between the two samples were shown with respect to socio-demographic, criminological, and psychiatric variables using bivariate logistic regressions. In the second analysis, recidivism was estimated separately for both samples, using a logistic regression model as a function of a set of psychiatric, socio-demographic and criminological variables. Bivariate logistic regression showed that different risk factors for recidivism existed for both samples. Forensic risk assessment models are very sensitive to the calibration sample. There is strong evidence that, even when index-offenses and the socio-cultural background are the same, risk factors for recidivism differ depending on the stage of the judicial process in which the subjects are (e.g. whether a subject is indicted, on conditional release, on parole, or no longer under the supervision of a parole board). Unfortunately, none of the currently available actuarial risk assessment instruments that have been validated in European countries consider the different stages of the judiciary process.

Risk assessment and prediction of criminal recidivism in psychiatric patients

Risk assessment and prediction of criminal recidivism in psychiatric patients

The Prediction of Criminal Recidivism in Juveniles

A meta-analysis was conducted to identify risk factors that best predict juvenile recidivism, defined as rearrest for offending of any kind. Twenty-three published studies, representing 15,265 juveniles, met inclusion criteria. Effect sizes were calculated for 30 predictors of recidivism. Eight groups of predictors were compared: (a) demographic information, (b) offense history, (c) family and social factors, (d) educational factors, (e) intellectual and achievement scores, (f) substance use history, (g) clinical factors, and (h) formal risk assessment. The domain of offense history was the strongest predictor of reoffending. Other relatively strong predictors included family problems, ineffective use of leisure time, delinquent peers, conduct problems, and nonsevere pathology.

Evidence for the Efficacy of Self-Report in Predicting Nonviolent and Violent Criminal Recidivism

Self-report instruments have not been favored in the prediction of criminal recidivism. The present study compared the predictive accuracy of a self-report instrument (Self-Appraisal Questionnaire) with the Psychopathy Checklist-Revised, General Statistical Information on Recidivism, and the Violent Risk Appraisal Guide. The sample consisted of incarcerated males (N= 78) who were followed for 2 years following release. Of the four risk prediction instruments, the Self-Appraisal Questionnaire was statistically equivalent in predicting nonviolent and violent recidivism. These results suggest that a self-report instrument can predict recidivism.

Predicting criminal recidivism using neural networks

Prediction of criminal recidivism has been extensively studied in criminology with a variety of statistical models. This article proposes the use of neural network (NN) models to address the problem of splitting the population into two groups — non-recidivists and eventual recidivists — based on a set of predictor variables. The results from an empirical study of the classification capabilities of NN on a well-known recidivism data set are presented and discussed in comparison with logistic regression. Analysis indicates that NN models are competitive with, and may offer some advantages over, traditional statistical models in this domain.