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

Re: st: RE: loglinear models and survey data


From   "Brian P. Flaherty" <bxf4@u.washington.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: RE: loglinear models and survey data
Date   Thu, 29 Sep 2005 13:31:28 -0700

On Sep 29, 2005, at 1:13 PM, Nick Cox wrote:

I think that -contract- leading to -glm- is indeed the
best route. One of the details of -contract-, the -zero-
option, was included with this very task in mind.
Thank you very much for such a quick reply.

I am not clear on the difficulty with pweights. Can't
you just include the weight variable in the list supplied
to -contract-? I don't think you need a separate handle
to treat them differently.
The contract help page and book says that only fweights are allowed. When I try with my weight (which is not integer), I get the following error messages:

. contract cigever alcever mjever [weight=analwt_c], freq(count)
(frequency weights assumed)
may not use noninteger frequency weights
r(401);

. contract cigever alcever mjever [pweight=analwt_c], freq(count)
pweight not allowed
r(101);

. contract cigever alcever mjever [fweight=analwt_c], freq(count)
may not use noninteger frequency weights
r(401);

Am I calling it incorrectly or misunderstanding something else?

Brian

*
* 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