Evaluating the discriminatory power of a multiple logistic regression model

Abstract

Various measures for estimating the goodness-of-fit of the multiple logistic regression (MLR) model have been suggested, although there is no clear consensus as to which measure is most suitable. In this paper, a simple measure of the discriminatory power of the fitted MLR model, based on maximization of Youden's J index (J*), is proposed and compared with several goodness-of-fit statistics described previously. The relative effectiveness of the measure is illustrated using data from the Lipid Research Clinics Prevalence Study. It is suggested that J* may be a useful alternative index of goodness-of-fit of an MLR model, with the added advantage of having a simple practical interpretation.