This study examines the statistical validation of a recently developed, fourth-generation (4G) risk—need assessment system (Correctional Offender Management Profiling for Alternative Sanctions; COM...

http://www.northpointeinc.com/files/publications/Criminal-Justice-Behavior-COMPAS.pdf

Evaluating the Predictive Validity of the Compas Risk and Needs Assessment System

We conducted a comprehensive meta-analysis of the Level of Service (LS) scales, their predictive accuracy and group-based differences in risk/need, across 128 studies comprising 151 independent samples and a total of 137,931 offenders. Important potential moderators were examined including ethnicity, gender, LS scale variant, geographic region, and type of recidivism used to measure outcome. Results supported the predictive accuracy of the LS scales and their criminogenic need domains for general and violent recidivism overall, and among broad subgroups of interest, including females and ethnic minorities. Although results indicated that gender and ethnicity were not substantive sources of effect size variability, significant differences in effect size magnitude were found when analyses were conducted by geographic region. Canadian samples consistently demonstrated the largest effect sizes, followed by studies conducted outside North America, and then studies conducted in the United States. This pattern was observed irrespective of gender, ethnicity, LS domain, LS variant, or type of recidivism outcome, suggesting geographic region may be an important source of effect size variation. We discuss possible factors underlying this pattern of results and identify areas for future research.

Thirty years of research on the level of service scales: a meta-analytic examination of predictive accuracy and sources of variability.

Analysis of predictive validity of the risk/needs assessment used by a criminal justice agency is paramount. The validity of the Positive Achievement Change Tool (PACT) across gender/race/ethnicity in a juvenile sample was examined. Results demonstrate recidivism increases as PACT score increases, with minor exceptions. Findings suggest similar prediction of referral/arrest and adjudication/conviction across subgroups. 95% confidence intervals overlapped for all subgroups on 13 of 19 measures examined. However, which factors predict recidivism across subgroups differ. Criminal history was the most prevalent predictor, while no factor predicted White female offending. “Gender-responsive” item inclusion measuring abusive/traumatic circumstances did not improve prediction.

Examining the Validity of a Juvenile Offending Risk Assessment Instrument Across Gender and Race/Ethnicity

With the population of adults under correctional supervision in the United States at an all-time high, psychologists and other professionals working in U.S. correctional agencies face mounting pressures to identify offenders at greater risk of recidivism and to guide treatment and supervision recommendations. Risk assessment instruments are increasingly being used to assist with these tasks; however, relatively little is known regarding the performance of these tools in U.S. correctional settings. In this review, we synthesize the findings of studies examining the predictive validity of assessments completed using instruments designed to predict general recidivism risk, including committing a new crime and violating conditions of probation or parole, among adult offenders in the United States. We searched for studies conducted in the United States and published between January 1970 and December 2012 in peer-reviewed journals, government reports, master's theses, and doctoral dissertations using PsycINFO, the U.S. National Criminal Justice Reference Service Abstracts, and Google. We identified 53 studies (72 samples) conducted in U.S. correctional settings examining the predictive validity of 19 risk assessment instruments. The instruments varied widely in the number, type, and content of their items. For most instruments, predictive validity had been examined in 1 or 2 studies conducted in the United States that were published during the reference period. Only 2 studies reported on interrater reliability. No instrument emerged as producing the "most" reliable and valid risk assessments. Findings suggest the need for continued evaluation of the performance of instruments used to predict recidivism risk in U.S. correctional agencies. (PsycINFO Database Record

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

Gridlock or mutability: Reconsidering “gender” and risk assessment†

Over the past two decades, the role of risk-needs assessment in the criminal justice system has increased substantially. This study provides validation data on the Level of Service Inventory–Revised (LSI-R) and the Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) using a large male cohort (N = 975) with a substantial proportion of ethnic minority offenders. In comparing the predictive validity of these tools, the authors employed a retrospective, archival, knowngroups design to study outcomes of offenders released into the community from New Jersey prisons between 1999 and 2002, with a postrelease outcome period of 12 months. The results indicate that both the LSI-R composite score and the COMPAS recidivism score have inconsistent validity when tested on different ethnic/racial populations. Furthermore, the results suggest that different ethnic/racial groups have varying risk and needs factors that predict recidivism.

https://www.drexel.edu/~/media/Files/psychology/labs/heilbrun/papers/The%20LSI-R%20and%20the%20COMPAS%20-%20Validation%20data%20on%20two%20risk-needs%20tools.ashx

Tracy L. Fass

Papers

The LSI-R and the Compas: Validation Data on Two Risk-Needs Tools