If you have censored data or time-varying covariates, better to use the cox
regression model.
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Wendy Regoeczi
Sent: Friday, April 27, 2007 12:51 PM
To: [email protected]
Subject: Re: st: RE: testing for significant differences between
coefficients in different models
Thanks for the clarification. That works. But
apparently Stata won't conduct the test if the
models are different types. Using the lrtest
command after the second model, the tests are not
conducted. Instead, I get an error message
reading: "test involves different estimators: logistic vs. cox"
At 12:42 PM 4/27/2007, you wrote:
>The command is:
>
>est store
>
>Best,
>J.
>
>----- Original Message -----
>Exp�diteur: Wendy Regoeczi <[email protected]>
>�: [email protected]
>Sujet: Re: st: RE: testing for significant differences
>between coefficients in different models
>Date: Fri, 27 Apr 2007 12:40:30 -0400
>
> > Thanks for the suggestion. I just tried it, but I get an
> > error message reading "unrecognized command: store"
> > I tried typing the command after I ran the model, and also
> > including at the end of the model statement before
> > running the model, but both ways result in error
> > messages. Am I doing something wrong?
> >
> > At 12:11 PM 4/27/2007, you wrote:
> > >Use the likelihood ratio test.
> > >
> > >After the first model write:
> > >
> > >Store estimates A
> > >
> > >After the second model write:
> > >
> > >Store estimates B
> > >Lrtest A
> > >
> > >Cynthia Fontanella
> > >[email protected]
> > >
> > >-----Original Message-----
> > >From: [email protected]
> > >[mailto:[email protected]] On Behalf
> > Of Wendy Regoeczi >Sent: Friday, April 27, 2007 11:37 AM
> > >To: [email protected]
> > >Subject: st: testing for significant differences between
> > coefficients in >different models
> > >
> > >Hello all,
> > >I couldn't find an answer to this question in the
> > archives. I am >analyzing two models using the same set of
> > independent variables, one >is a logistic regression model
> > and the other is a Cox proportional >hazards model. It has
> > been suggested to me that I should do some >post-hoc tests
> > of the differences between the coefficients in the two
> > >models. Is there a way to do this in Stata, given that
> > two different >types of models are being estimated and the
> > variable names are >identical in both models?
> > >
> > >Any help would be greatly appreciated!
> > >Sincerely,
> > >Wendy Regoeczi
> > >
> > >*
> > >* 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/
> >
> > *
> > * 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/
>
>___________________________________
>
>Prof. John Antonakis
>Faculty of Business and Economics
>University of Lausanne
>Internef #527
>CH-1015 Lausanne-Dorigny
>Switzerland
>
>Tel: ++41 (0)21 692-3438
>Fax: ++41 (0)21 692-3305
>
>http://www.hec.unil.ch/jantonakis
>___________________________________
>
>*
>* 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/
*
* 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/
