1The Use of Actuarials at Civil Commitment Hearings to Predict the Likelihood of Future Sexual Violence by

The civil commitment of so-called “sexually violent predators ” requires that a prediction be made regarding the likelihood that a given individual will engage in future acts of “sexual violence. ” In an effort to make any such prediction as accurate as possible, a variety of actuarial methods have been proposed. Utilizing an actuarial method to make a prediction involves documenting the existence of a statistical correlation between the presence of certain “risk factors ” and a particular outcome. For example, when setting premium costs, a medical insurance company needs to have some sense of which groups of individuals are likely to be at heightened risk of having a heart attack in the future. A group that likely would be at such a heightened risk would be one made up predominately of obese, cigarette smoking males, who had both hypertension and high levels of cholesterol. It is critical to note that individuals within any such “high risk ” group are not all at equal risk. Thus, cardiac angiography, which is capable of revealing differences amongst individuals within such a group, would likely document that some have significantly clogged coronary arteries, whereas others do not. That could be one reason why many men within that so-called “high risk ” group will nevertheless still not have a heart attack. Documenting that a given percentage of persons within any previously screened group (e.g., 50%) are likely to have a predicted outcome (e.g., either a heart attack, or future sexual misconduct) does not mean that each individual within that group is himself at a 50 % risk. Some may be at a 70 % risk, and others at 30%. Ordinarily, actuarial methods cannot distinguish one from the other. Absent accurate statistical confidence levels, one may not even be clear about the range of risk applicable to any given individual within such a group