Federal Correctional Institution, Schuylkill, PA, USA.
Assessment. 2011 Jun;18(2):227-33. doi: 10.1177/1073191110397484. Epub 2011 Jan 27.
The possibility of combining indicators to improve recidivism prediction was evaluated in a sample of released federal prisoners randomly divided into a derivation subsample (n = 550) and a cross-validation subsample (n = 551). Five incrementally valid indicators were selected from five domains: demographic (age), historical (prior convictions), adjustment (prior incident reports), rating scale (Violation scale of the Lifestyle Criminality Screening Form), and self-report (General Criminal Thinking score from the Psychological Inventory of Criminal Thinking Styles). After converting scores on the five indicators to a common scale (z score), two combined scores were calculated: a simple summed score (unweighted summed score) and a score computed using beta weights from a Cox survival analysis of the derivation subsample (weighted summed score). Correlational and receiver operating characteristic analyses revealed that the unweighted and weighted summed scores produced equivalent results and that both improved significantly on the results of the five contributing indicators.
在一个随机分为推导子样本（n=550）和交叉验证子样本（n=551）的已释放联邦囚犯样本中，评估了组合指标以提高累犯预测的可能性。从五个领域中选择了五个逐步有效的指标：人口统计学（年龄）、历史（先前的定罪）、调整（先前的事件报告）、评分量表（生活方式犯罪筛查表的违规量表）和自我报告（犯罪思维风格心理问卷的一般犯罪思维得分）。将五个指标的分数转换为共同的量表（z 分数）后，计算了两个综合分数：一个简单的总和分数（未加权总和分数）和一个使用推导子样本的 Cox 生存分析的β权重计算的分数（加权总和分数）。相关和接收者操作特征分析表明，未加权和加权总和分数产生了等效的结果，并且都明显优于五个贡献指标的结果。
