The Construction and Selection of Predictive Scales, With Special Reference to Parasuicide

Issues concerning the use of predictive & screening instruments include the difficulties posed by temporal changes in the base rates for the behaviour of interest, the possible advantage of using 3 rather than 2 risk categories, & the desirability of specifying in advance the proportional sizes of the risk subgroups. A method for constructing & assessing tripartite risk scales, & a new scale for predicting repetitive parasuicide, with the results of a prospective validation study, is reported.