Prediction of gradual release violations and institutional misconduct with actuarial risk assessment instruments-A retrospective validation study of the OGRS 3 and the SVG-5

Actuarial risk assessment instruments are regarded as an essential part of state of the art appraisals of the likelihood of recidivism of individuals released from the prison system; however, their accuracy and clinical relevance for the prediction of gradual release violations and institutional misconduct have been relatively rarely investigated. Therefore, the present study examined the predictive accuracy of two actuarial risk assessment instruments, the third version of the Offender Group Reconviction Scale (OGRS 3) and the Screening Instrument for the Prediction of Violent Recidivism (SVG-5), for specifically predicting these two outcome variables. In addition, the predictive potential of further predictor variables was analyzed. A sample of 200 inmates from the correctional facility in Frankenthal (Rhineland-Palatinate, Germany) was retrospectively collected. Both risk assessment instruments achieved predominantly low effect sizes (OGRS 3: Area Under the Curve (AUC) = 0.522-0.556 and SVG-5 AUC = 0.561-0.653); however, due to methodological limitations of this study, the results should be interpreted cautiously, but could be regarded as a promising starting point for future research given the basic predictability of gradual release violations and institutional misconduct.