Statalist The Stata Listserver


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

Re: st: Obtaining Predicted Probabilities using gologit


From   Richard Williams <Richard.A.Williams.5@ND.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Obtaining Predicted Probabilities using gologit
Date   Wed, 14 Jun 2006 10:14:44 -0500

At 08:40 AM 6/14/2006, Nick Winter wrote:
my -oprobpr- might be of service here (although it doesn't work, I think, after gologit. But you could hack into it potentially).

Also check out -adjust-

--Nick
As luck would have it, I had an exchange with Stata tech support a while back about the use of adjust with the pr option after gologit2. Here is what I wrote:

***I wrote a customized predict command (gologit2_p) for my gologit2 program so I could compute predicted probabilities. Alas, adjust still won't let me use the -pr- option after running gologit2. Just skimming through adjust.ado, it appears that your program needs to be officially "blessed" (i.e. explicitly mentioned in the adjust.ado code) for the pr option to work. Is there a way to get your program blessed, or to otherwise work around
this? Thanks.***

Stata's response:

***The -pr- option of -adjust- is not passed on to -predict-. As with -exp-, -adjust- does the transform itself; a consequence of this is that -adjust- will only allow the -pr- options for estimation results it recognizes.***

So in general, many post-estimation commands will not work or will have only limited functionality with user-written commands. You therefore may have to improvise a bit to get what you want. (As a sidelight, my mfx2 program does many of the same things as margeff. margeff is often much faster; but mfx2 works with more programs. I wrote mfx2 partly because margeff did not work with my programs and some other commands that were added in Stata 9).




-------------------------------------------
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