Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Re: Problem with xttest2
From
Kit Baum <[email protected]>
To
"Elisabeth Kutschka" <[email protected]>
Subject
st: Re: Problem with xttest2
Date
Fri, 5 Mar 2010 10:11:09 -0500
The reason for that is usually that you have more units in the panel than observations on each unit. That would cause -sureg- to fail with a singular VCE of the residuals, and as this test is looking at that VCE, it cannot handle it either. A matrix with g columns cannot have full column rank if it has fewer then g rows, and in this case the xtgls residuals form such a matrix.
Kit
On Mar 5, 2010, at 9:18 AM, Elisabeth Kutschka wrote:
> Dear Mr. Baum,
>
> I used your STATA module "xttest2" to perform Breusch-Pagan LM test for
> cross-sectional correlation after xtgls-Regression. (I use STATA 10)
> However, the test does not work and the error message is: "Correlation
> matrix of residuals is singular. not possible with test r(131)".
>
> Is there any way to solve this problem? Thank you very much for your help!
>
> With best regards,
> Elisabeth Kutschka
>
>
> ______________________________
>
> Dipl.-Vw. Elisabeth Kutschka
> Otto-von-Guericke-Universität Magdeburg
> Lehrstuhl für Internationale Wirtschaft
> Postfach 4120
> D-39106 Magdeburg
> Tel.: (49)391 67 11 645
> Fax: (49)391 67 11 177
>
>
>
Kit Baum | Boston College Economics & DIW Berlin | http://ideas.repec.org/e/pba1.html
An Introduction to Stata Programming | http://www.stata-press.com/books/isp.html
An Introduction to Modern Econometrics Using Stata | http://www.stata-press.com/books/imeus.html
*
* 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/