Originally I wanted to have ROC area (as calculated in -diagt-), but I was
told that with a dichotomous test ROC area wasn't relevant, ie, I didn't
have different cutpoints at which to operate the test. That's when she
mentioned accuracy defined with prevalence.
In fact, ROC area doesn't account for prevalence either...
The ROC area is still useful, because it is the Mann Whitney statistic -
the probability that if a person with and a person without the condition
are taken at random, the person with the condition will have the higher
score. In clinical trials, it becomes the probability that a person on the
superior treatment will have a superior response. Both are very useful
clinical information.
