[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: SDT/ROC equal variance test

From   James <>
Subject   st: SDT/ROC equal variance test
Date   Thu, 23 Apr 2009 10:31:50 -0500

I'm working on an SDT problem and the key hypotheses I'm testing requires the equal-variance assumption to hold. Is there a way to test this with the roc functions? I assume there is and am justing missing it. What I have so far:

1. roctab produces a nice monotonic convex ROC curve. But this is a non-parametric test so I'm not sure that helps much.

2. the slope coefficient in rocfit is .97. Is that the slope of the z-transformed ROC, which presumably would mean I'm good to go. Does the fact that the ROC areas are similar across the non-parametric & binormal models do anything for me?

Thanks much.


*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index