LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous (more recent) messageNext (less recent) messagePrevious (more recent) in topicNext (less recent) in topicPrevious (more recent) by same authorNext (less recent) by same authorPrevious page (May 2001, week 2)Back to main SAS-L pageJoin or leave SAS-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Mon, 14 May 2001 12:00:39 -0400
Reply-To:     Reshama Shaikh <reshama@EMAIL.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Reshama Shaikh <reshama@EMAIL.COM>
Subject:      finding "AREA" under roc curve (4)
Content-Type: text/plain; charset=us-ascii

I am running SAS V8. What I actually need is the "AREA" under the curve. I know there is output that gives you the coordinates to plot the curve, but how do I compute the "AREA"? Also, I will need the standard error of the area since I am making comparisons with other ROC curves.

Any help is greatly appreciated.

(1) Reshama Shaikh wrote: > Would anyone have a macro that calculates the area under the curve of x,y points for PROC LOGISTIC? (2) Date: Wed, 9 May 2001 14:24:07 -0700 From: Ramzi Mrad <mradramz@WELLSFARGO.COM> Subject: Re: macro for ROC curve You don't need a macro. In the logistic, use the /ctable option after model=.... and output the result to a file using output out=... The file you output will include 2 variables, one called "_sensit_" (sensitivity) and the other called "_1mspec_" (1-specificity), plotting these against each other gives you the ROC. Ramzi (3) Date: Wed, 9 May 2001 13:57:57 -0700 From: "David L. Cassell" <Cassell.David@EPAMAIL.EPA.GOV> Subject: Re: macro for ROC curve Could you tell us what version of SAS you are running? Because SAS v8 does this for you. It's the "c" statistic that is [IIRC] part of the default output. David

----------------------------------------------- FREE! The World's Best Email Address @email.com Reserve your name now at http://www.email.com


Back to: Top of message | Previous page | Main SAS-L page