Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: ROC question: STATA vs SPSS
From
Richard Williams <[email protected]>
To
[email protected], "[email protected]" <[email protected]>
Subject
Re: st: ROC question: STATA vs SPSS
Date
Thu, 28 Jul 2011 16:16:23 -0500
At 02:53 PM 7/28/2011, Danielle Boyce wrote:
Hi,
I usually use STATA for my data analysis, but for various reasons,
ran one in SPSS first. It gave me a negative cutoff point when my
data have no negative values. I re-ran in STATA and got the same
AUC, but no negative cutoff, and everything else (CIs, cutoffs) are
ever-so-slightly off compared to SPSS.
I'm just wondering if anyone knows why this discrepancy exists.
Thanks!
Danielle
I don't know specifically about ROC, but often such differences are
due to differences in parameterization. One program might do 0 versus
1 while another does 1 versus 0. Or, one program adds a constant
while another subtracts a cutpoint. If possible, try to compare how
the two programs are parameterizing things.
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* 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/