Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Hausman test


From   clivelists@googlemail.com
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Hausman test
Date   Thu, 9 Aug 2012 12:25:06 +0000

An alternative is to calculate mean-deviations and group-specific means for each time-varying covariate, run your -rologit- model with all of them and then use -testparm- to conduct an F test for the additional variables. If F is significant, you retain the fixed effects in your model, which is surely what the Hausman test is there for.

C

-----Original Message-----
From: Elizabeth Vieira <za@portugalmail.com>
Sender: owner-statalist@hsphsun2.harvard.edu
Date: Thu, 9 Aug 2012 12:31:18 
To: <statalist@hsphsun2.harvard.edu>
Reply-To: statalist@hsphsun2.harvard.eduSubject: st: Hausman test

Hello

I am using the rank ordered logistic regression. When I run the
Hausman test I get the following message"V_b-V_B is not positive
definite" in some cases and a negative Chi-Square “model fitted on
these data fails to meet the asymptotic assumptions of the Hausman
test” in another. The suest test is recommended, but this cannot be
used with rologit. How I solve this problem?

Best regards

Elizabeth

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   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   |   Site index