Re: st: RE: what T/N relation in sureg?

[Jon Eckhardt <jeckhardt@wisc.edu>]

ok


--On Wednesday, July 09, 2003 12:00 PM +0100 Nick Cox 
<n.j.cox@durham.ac.uk> wrote:


> MKF.Poschke@student.unimaas.nl
>
> > I am trying to conduct a SUR on a panel dataset using
> > -sureg-, with one
> > equation per country. However, unless I use only a very
> > small number of
> > equations, I always get the error message "insufficient
> > observations", even
> > if T > 2M (time dimension more than twice as large as
> > number of equations).
> > It is quite obvious that T has to be larger than M, but by
> > how much? I could
> > not find details on this question anywhere. Does maybe
> > anybody of you know?
> > (Or is it maybe so obvious that it should jump to my eyes?)
> The criteria behind this appear to emanate from -reg3-.
> Examination of documentation or the source code, reg3.ado,
> might help here.
>
> Nick
> n.j.cox@durham.ac.uk
> *
> *   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/


Jon Eckhardt, Ph.D.
Assistant Professor
Department of Management & Human Resources
The Weinert Center for Entrepreneurship
University of Wisconsin--Madison



*
*   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/