Comparison and combination of clinical and statistical predictions of recidivism among adult offenders.

Abstract

Clinical and statistical predictions of six categories of recidivism among 198 adult male felony probationers were compared and combined, both before and after correcting for the restricted range of the predictor vanables The statistical composite consistently outperformed decision makers for the undifferentiated recidivism catena of arrest and conviction The opposite state of affairs was seen to exist for all three indices of violent recidivism, but only after correction for restriction of range The combination of both variables tended not to produce significant increases m criterion variance compared to the superior predictor alone, the major exception being incarceration for any offense Decision makers performed best when forecasting violent criminal conduct that resulted m incarceration, and this contingency table was subjected to a detailed analysis of the outcomes of prediction This included two methods of estimating the probable probationary performance of 141 members of the initial sample who were sentenced to pnson and consideration of the utilities associated with false positive and false negative errors Partially because of the seeming impossibility of achieving perfect prediction, it was concluded that there is a need for decision-making guidelines that include only those cnminological vanables that can serve the dual purpose of predicting recidivism and indicating which offenders, because of the social harm for which they have been responsible, are the most deserving of impnsonment as punishment

Performance of recidivism risk assessment instruments in U.S. correctional settings.

“…b) The SAQ, the only included instrument designed to be self-administered, was not be administered by either a researcher or professional. c) Of those eight (11.1%) samples for which demographic characteristics were reported for samples before participant attrition, five (6.9%) had more than 25% attrition during follow-up (Dow et al, 2005;Fass, Heilbrun, DeMatteo, & Fretz, 2008;Holland, Holt, Levi, & Beckett, 1983;Miller, 2006;Millson et al, 2010). d) Fixed-effects mean.…”

The Organizational Politics of Implementing Risk Assessment Instruments in Community Corrections

“…early interest in the use of risk assessment in community corrections focused on the nature of assessment itself, including determining which method of assessment (i.e., clinical or actuarial) was most efficacious. a series of analyses (some conducted on corrections populations, some not) established that actuarial methods of risk prediction nearly always outperform clinical judgment (grove & Meehl, 1996;Harris, 2006;Holland, Holt, Levi, & Beckett, 1983;Taxman, 2006).…”

Violence risk assessment: combining actuarial and clinical information to structure clinical judgements for the formulation and management of risk

“…Some well‐known examples are 1970s studies, such as Steadman & Cocozza (1974) and Thornberry & Jacoby (1979). Later studies include Holland et al . (1983), Sepejak et al .…”