Notice: On March 31, it was **announced** that Statalist is moving from an email list to a **forum**. The old list will shut down on April 23, and its replacement, **statalist.org** is already up and running.

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

From |
Massimiliano Sassone <massimilianosassone@gmail.com> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
st: Hausman test, rank of the differenced variance matrix, (V_b-V_B is not positive definite) |

Date |
Fri, 12 Apr 2013 09:40:11 +0800 |

Dear all, I ran the Hausman test to check which method, between fixed and random effects, is more appropriate. I'm using Stata 11 to analyze a panel dataset composed of 279 observations, derived from 31 regions over a 9-year period. When I run the test, apart from the (V_b-V_B is not positive definite) note at the bottom, I also incur in the following note:"the rank of the differenced variance matrix (8) does not equal the number of coefficients being tested (9)." I tried to run the test with the sigmaless/sigmamore options, as recommended in previous posts, and the (V_b-V_B is not positive definite) note disappears. I couldn't understand the meaning of the second note, the one regarding the rank of the differenced variance matrix. How is this interpreted? Does it represent a problem in the model? Could anybody give me a hint? It would be greatly appreciated. Thank you very much Massimiliano (Max) Sassone * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/

- Prev by Date:
**Re: st: Is there an -mi drop- command?** - Next by Date:
**st: How does Stata’s ml handle missing log-likelihood values?** - Previous by thread:
**st: comparing biprobit marginal effects CIs** - Next by thread:
**st: How does Stata’s ml handle missing log-likelihood values?** - Index(es):