You are not currently logged in.
Access JSTOR through your library or other institution:
Further Comments on Portraying the Accuracy of Violence Predictions
Law and Human Behavior
Vol. 18, No. 5 (Oct., 1994), pp. 587-593
Published by: Springer
Stable URL: http://www.jstor.org/stable/1394258
Page Count: 7
Preview not available
Hart, Webster, and Menzies (1993) recently offered several recommendations for describing the accuracy of violence predictions using 2 × 2 contingency tables. This Comment describes some problems with their recommendations and suggests that researchers use receiver operating characteristic (ROC) analysis to quantify prediction accuracy.
Law and Human Behavior © 1994 Springer