Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: predict after svy logit

From   Nick Winter <>
Subject   Re: st: predict after svy logit
Date   Wed, 15 Jun 2005 14:59:12 -0400


-svy : oprobit- does seem to give correct predictions (that is, it seems to predict probabilities, not xb's), so that is a work-around for now, as well.

--nick Winter

At 01:46 PM 6/15/2005, you wrote:

At 01:19 PM 6/15/2005 -0400, Nick Winter wrote:
Looking at the structure of the predict command under version 8, I think the problem is that the version 9 predict routine does not properly transform the output of _predict.

But I'm sure StataCorp will be on this quickly.

BTW, the problem affects svy: probit as well.
I bet you are right. In 8.2, there was a separate predict routine for svylogit/svyprobit, which had special code for handling the -pr- option. But, in 9.0, there is just logit_p.ado. So, either you need more specialized code for -svy- in logit_p.ado or _predict needs to be revised. (That is my wild guess anyway!)

Incidentally, I notice svy works with mlogit, so you can use it instead of logit; but svy doesn't seem to work with mprobit. I wonder why?

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):
WWW (department):

* For searches and help try:
Nicholas Winter                           607.255.8819 t
Assistant Professor                       607.255.4530 f
Department of Government     e
308 White Hall   w
Cornell University
Ithaca, NY 14853-4601

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index