Thanks Roberto.
M�nica L.
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Roberto G.
Gutierrez, StataCorp
Sent: Sunday, December 05, 2004 6:08 PM
To: [email protected]
Subject: Re: st: streg: why Stata doesn't report LR test ...
Monica L. Parra Torrado <[email protected]> asks:
> Hi, I posted this question yesterday and after some work I realized that
> Stata does not report the LR test when I am using pweights. I have done
all
> my estimations using these weights so I set the weights from the beginning
> in the stset command. But it seems that not all the streg commands work
> when using the weights (see for example a related question and answers on
> pweights and stcurve that I posted yesterday: "stcurve does not allow
> pweights?"). So, how can I estimate the LR test after using the weights?
> And an alternative to the stcurve command? Any suggestions on what should
I
> do?
Likelihood ratio tests are not appropriate when pweights and/or robust
variance of estimators are requested. See
http://www.stata.com/support/faqs/stat/lrtest.html
for the gory details.
As to why -stcurve- doesn't work with pweights, this was a bug that was
fixed sometime ago. If you update your Stata, you should be fine.
--Bobby
[email protected]
*
* 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/
*
* 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/
