st: RE: message (V_b-V_B is not positive definite) in hausman test

["Fredrik Wilhelmsson" <Fredrik.Wilhelmsson@nek.lu.se>]

I don't think one can interpret the Hausman test in this case, but there is an omitted variables version of the Husman test that might be appropriate see B. H. Baltagi (2002) "Econometric Analysis of Panel Data" Ch.4 in the second ed.  

/Fredrik

-----Ursprungligt meddelande-----
Fr�n: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] F�r Christine Lee
Skickat: den 1 juli 2005 13:32
Till: statalist@hsphsun2.harvard.edu
�mne: st: message (V_b-V_B is not positive definite) in hausman test

Hi

I ran a hausman test between fixed and random effects models and got the
message   (V_b-V_B is not positive definite) at the end of the estimation.

Has anyone got a clue what this is and ways of resolving this?

Thanks
Christine Lee

*
*   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/