Classification Tree Approach to the Development of Actuarial Violence Risk Assessment Tools

• NCJ Number: 181520
• Journal: Law and Human Behavior Volume: 24 Issue: 1 Dated: February 2000 Pages: 83-100
• Author(s): Henry J. Steadman; Eric Silver; John Monahan; Paul S. Appelbaum; Pamela C. Robbins; Edward P. Mulvey; Thomas Grisso; Loren H. Roth; Steven Banks
• Editor(s): Richard L. Wiener
• Date Published: February 2000
• Length: 18 pages
• Publication Format: Article
• Language: English
• Country: United States of America

Annotation

This article describes a classification tree approach to developing actuarial violence risk assessment tools.

Abstract

The article claims that, because most actuarial tools are based on a main effects regression approach, they do not adequately reflect the contingent nature of the clinical assessment processes. To enhance the use of actuarial violence risk assessment tools, it proposes a classification tree approach. In addition, it suggests that the use of two decision thresholds for identifying high- and low-risk cases--instead of the standard single threshold--may further enhance the use of actuarial tools to make dichotomous risk classification decisions. The results of this study reflect relatively short-term predictions of community violence among patients discharged from acute hospital stays. Statements of relative risk are in comparison to other discharged psychiatric patients and not in comparison to a general community sample. The extent to which these results will generalize to other settings, other patient populations or longer periods of observation is not known. Notes, tables, figures, appendixes, references