Thread: ROC curves - an appropriate use?

1. ROC curves - an appropriate use?

Hi all,

I am new to ROC curves. My only experience is using them to examine tests for a specific disease, however I wonder if my plans below are an acceptable use for ROC curves..

My data is as such:

Days on dialysis (kidney replacement) (days; and categorised into zero, <1 week of dialysis, >1 week dialysis)
Survival greater than 1 year (yes/no)

I'd be very grateful if someone can advise whether my scenario is compatible with a ROC curve.

Many thanks, David

2. Re: ROC curves - an appropriate use?

Yes, you can use a ROC curve for this, though you'll need to do some work. You can't really do it with the discretized version of days -- or rather, you could, but it would be boring. But the raw days measurement is close enough to continuous to make sense for ROC analysis. At a guess, (survival > 1 year) is negatively correlated with (days on dialysis), correct? So for some given number of days , you'd treat as a "positive days result" and as a "negative days result," and similarly as a "positive survival result" and as a "negative survival result." Here is the "gold standard", so, for example, is a false negative. Plot the results for where is the greatest number of days anyone spends on dialysis, and you have your ROC curve.

(Note: I may have the signs wrong, in which case the and signs up above should be reversed. But that's the general idea.)

3. The Following User Says Thank You to Daniel Dvorkin For This Useful Post:

dhmallon (04-08-2012)

4. Re: ROC curves - an appropriate use?

that makes perfect sense - thank you very much indeed!

5. Re: ROC curves - an appropriate use?

You're welcome!

One thing that occurred to me after I wrote this is that there's no reason to assume that or , so the curve you get out of this might not necessarily run from (0,0) to (1,1) like a traditional ROC curve, for a test where ), does. However, the curve will still be within the unit rectangle, and the area under the curve should still be a valid measure of the power of to predict .

Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts