User Guide

Chapter
41
ROC Curves
This procedure is a useful way to evaluate the performance of classification schemes
in which the
re is one variable with two categories by which subjects are classified.
Example. It is in a bank’s interest to correctly classify customers into those who will
and will not default on their loans, so special methods are developed for making these
decisions
. ROC curves can be used to evaluate how well these methods perform.
Statistics. Area under the ROC curve with confidence interval and coordinate points
of the ROC curve. Plots: ROC curve.
Methods. T
he estimate of the area under the ROC curve can be computed either
nonparametrically or parametrically using a binegative exponential model.
Data. Test variables are quantitative. They are often composed of probabilities from
discrimi
nant analysis or logistic regression or scores on an arbitrary scale indicating a
rater’s “strength of conviction” that a subject falls into one category or another.
The state variable can be of any type and indicates the true category to which a
subject b
elongs. The value of the state variable indicates which category should
be considered positive.
Assumptions. It is assumed that increasing numbers on the rater scale represent the
increas
ing belief that the subject belongs to one category, while decreasing numbers
on the scale represent the increasing belief that the subject belongs to the other
category. The user must choose which direction is positive.Itisalsoassumedthatthe
true cat
egory to which each subject belongs is known.
569