Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: order probit: SAS vs STATA


From   Richard Williams <Richard.A.Williams.5@ND.edu>
To   statalist@hsphsun2.harvard.edu, statalist@hsphsun2.harvard.edu
Subject   Re: st: order probit: SAS vs STATA
Date   Thu, 25 May 2006 13:49:42 -0500

At 11:39 AM 5/25/2006, Carol Bao wrote:
Hi, there,

I am wondering if anyone has attempted ordered probit
estimation using SAS as well as STATA?  We find that
the resuls (both the estimates on the threshold values
and the explanatory variables) are quite different
using the two software.  Is this "normal" and what the
explanations might be?  Any tips are highly
appreciated.
As Maarten says, SAS may be using a different but equivalent parameterization. Does SAS report a model likelihood ratio chi-square? Or, can you get predicted probabilities out of it? If so, you could compare these with Stata's results. If identical, you'll know you are dealing with equivalent models.

Also, check out this page:

http://www.indiana.edu/~statmath/stat/all/cdvm/cdvm5.html

I haven't looked at it carefully, but it appears to explain some of the differences between different programs. In particular, it has the line

"The estimated intercept of SAS is equivalent to (0-/cut1) in STATA. The _Limit2 of SAS is the difference between cut points of STATA, 1.91184=-10.83295-(-12.74479). "



-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX: (574)288-4373
HOME: (574)289-5227
EMAIL: Richard.A.Williams.5@ND.Edu
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* 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