Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: xtgls hetero


From   Kit Baum <baum@bc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: xtgls hetero
Date   Sat, 5 Jul 2003 12:06:09 -0400

On Saturday, Jul 5, 2003, at 02:33 US/Eastern, Rodrigo wrote:

I am phd student. I was running a xtgls estimation in Stata 7. After this I
tried to test the Breusch-Pagan Statistic for cross-section independence in
the residuals. I had a problem with that becuase my screen show me
"correlation matrix of residuals is singular not possible with test. Thanks
for help.

The residuals from an xt estimator, arrayed in a TxN matrix, where you have T obs on each of N panel units, are the "data" from which one wants to calculate this matrix of correlations. If you're trying to calculate such for N>T, it will be singular, since one cannot have more linearly independent vectors than the rank of the matrix, which cannot exceed T if N>T.

Kit

*
* 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/




© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index