Statalist


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

Re: st: ROC Curve plots


From   Svend Juul <SJ@SOCI.AU.DK>
To   <statalist@hsphsun2.harvard.edu>
Subject   Re: st: ROC Curve plots
Date   Tue, 14 Jul 2009 11:28:34 +0200

 
Stephan Rudolfer wrote:
 
I am working on a database of about 3,000 patients, and wish 
to plot the ROC curves of various diagnostic algorithms 
based on logistic regression, using roctab and roccomp.  
Perhaps unsurprisingly, the plots are very "fuzzy", 
presumably since the cutpoints generated depend on the total 
number of patients in the database and hence are too numerous?
 
My question: Is it possible to get a "cleaner" ROC curve plot?  
The roc routines don't seem to allow any control of the number 
of cutpoints used for the ROCC.
 
========================================================
 
Steve pointed to some solution. Another possibility is -rocfit-
followed by -rocplot-. In the -rocplot- command I also included
some options that in my opinion improve the graph.
 
     ----------------------------------------
     rocfit refvar classvar, continuous(10)
     
     rocplot , ///
        plotopts(msymbol(i)) ///
        lineopts(lpattern(l)) ///
        aspectratio(1) ///
        plotregion(margin(zero)) ///
        ylabel(, nogrid) xlabel(, nogrid)
     ----------------------------------------
 
Hope this helps
Svend

________________________________________________________ 
 
Svend Juul
Institut for Folkesundhed, Afdeling for Epidemiologi
(School of Public Health, Department of Epidemiology)
Bartholins Allé 2
DK-8000 Aarhus C,  Denmark 
Phone:   +45 8693 7796 
Mobile:  +45 2634 7796
E-mail:  sj@soci.au.dk 
_________________________________________________________ 

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index