Examining the Predictive Validity of the Static-99R on Native American Sex Offenders

Abstract

Abstract No study to date has evaluated the predictive validity of the Static-99R on a sample of Native American sex offenders. This study provides such an investigation. Findings reveal the Static-99R demonstrates small predictive validity for new sexual recidivism charges (AUC = 0.599) at five years for all offenders. However, the predictive validity for the sample of Native American sex offenders reaches moderate predictive validity (AUC = 0.672) when examined separately. Additional metrics beyond area under the curve analyses are used to assess the three dimensions of predictive validity: accuracy, discrimination, and calibration. Implications of the findings are discussed.