A classification tree approach to the development of actuarial violence risk assessment tools

Since the 1970s, a wide body of research has suggested that the accuracy of clinical risk assessments of violence might be increased if clinicians use d actuarial tools. Despite considerable progress in recent years in the dev elopment of such tools for violence risk assessment, they remain primarily research instruments, largely ignored in daily clinical practice. We argue that because most existing actuarial tools are based on a main effects regr ession approach, they no not adequately reflect the contingent nature of th e clinical assessment processes. To enhance the use of actuarial violence r isk assessment tools, we propose a classification tree rather than a main e ffects regression approach. In addition, we suggest that by employing two d ecision thresholds for identifying high- and low-risk cases-instead of the standard single threshold-the use of actuarial tools to make dichotomous ri sk classification decisions may be further enhanced. These claims are suppo rted with empirical data from the MacArthur Violence Risk Assessment Study.