|
|  |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: RE: xtreg fe and matrix inversion error
Scott,
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of
> Scott Imberman
> Sent: 19 April 2006 17:04
> To: [email protected]
> Subject: st: xtreg fe and matrix inversion error
>
> Dear All,
>
> I am running some xtreg, fe estimates of the following form
>
> xi: xtreg depvar indepvars i.A*i.B, fe robust cluster(clustervar)
>
> I keep on getting the following error
>
> matrix not positive definite
> r(506)
>
> However, the error does not arrise if I do not use the robust
> command.
Do you get the error if you use robust but not cluster?
The main candidates for the error are either too many clusters (more
clusters than regressors), or a singleton dummy, i.e., a dummy that =1
for one observation only. The latter would cause problems with or
without cluster.
--Mark
> I would greatly appreciate if someone may be able to guide me
> to what i'm doing wrong. Thank you.
>
> Scott
>
> -------------------------------------------------------------------
> Scott Andrew Imberman
> Ph.D. Candidate in Economics
> University of Maryland
>
> 3105 Tydings Hall
> College Park, MD 20742
> Voice: (301) 405-3493
> Fax: (301) 405-3542
>
> [email protected]
>
> *
> * 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/
