Fw: st: How to deal with r(909) "op. sys. refuses to provide memory"??? xtgls

[Murod Aliyev <ma.statalist@yahoo.com>]

----- Forwarded Message -----
To: "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Cc: 
Sent: Sunday, 9 December 2012, 23:56
Subject: Re: st: How to deal with r(909) "op. sys. refuses to provide memory"??? xtgls

Dear Gordon

Thanks for your reply! Are you referring to Huber-White sandwich estimates, or anything else? I would appreciate any additional suggestions on what could be better than FGLS. Also, I can't think of anything better that would help me with autocorrelation, my tests show I do have it in my data.

Thanks!

Best wishes,
Murod


----- Original Message -----
From: Gordon Hughes <G.A.Hughes@ed.ac.uk>
To: statalist@hsphsun2.harvard.edu
Cc: 
Sent: Sunday, 9 December 2012, 12:08
Subject: Re: st: How to deal with r(909) "op. sys. refuses to provide  memory"??? xtgls

You should also think very hard about whether it makes sense to use xtgls for this purpose.  There are all sorts of warnings, in Stata documentation and the literature, about the reliability of xtgls in these circumstances.  Technical problems of the kind that you encountered are all too often an indication of a poorly conceived model.

With very large N and rather small T you cannot possibly obtain sensible estimates of either within panel autocorrelation or across panel correlation.  As a consequence all you can estimate is a model with heteroskedastic panel errors.  There are much better ways in Stata of dealing with this than by using xtgls.

Regards

Gordon Hughes
g.a.hughes@ed.ac.uk

======================

You have 4 Gb of RAM, but it's typical that Windows only provides
about half to Stata. You need more RAM, i.e. a hardware change, to run
precisely this model. Otherwise you try using fewer groups or shutting
other applications (which probably won't make much difference).

Nick

On Sun, Dec 9, 2012 at 10:28 AM, Murod Aliyev <ma.statalist@yahoo.com> wrote:

> I have read a lot of threads on this issue, but still can not resolve my problem:
>
> I am trying to run FGLS (xtgls) with 49,000 observations, 8 years unbalanced panel with around 7,500 groups, 26 varibles in the model.
> After first trying xtgls I get a message saying "matsize too small - should be at least 7369". So, I set matsize to 8000, then I get a message r(909) "op. sys. refuses to provide memory". Could you please help me understand what is causing the problem here, and how to reslve it? I presume it is not related to the number of observations or variables, but rather caused by the way FGLS works.
>


Re: st: How to deal with r(909) "op. sys. refuses to provide memory"??? xtgls  
*
*   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/

*
*   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/