Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: regress with 4000 x's is very slow


From   "Abdel Rahmen El Lahga" <rahmen.lahga@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: regress with 4000 x's is very slow
Date   Wed, 7 Nov 2007 21:56:12 +0100

you should use Mata it is very fast. In my computer (nort especially
fast) a regression with 4000 vars and 5000 observation took
0.42 hour.
HTH
AbdelRahmen

2007/11/7, Scott Merryman <scott.merryman@gmail.com>:
> You can recover the fixed effects estimates from -xtreg, fe- with
> -predict var, u-
>
> Scott
>
>
> On Nov 7, 2007 9:20 AM, Richard Boylan <rtboylan@gmail.com> wrote:
> > I am running regress with 4000 x's and it is very slow (if it gives me
> > an answer at all).
> >
> > I was wondering if there are any tricks that one can use to help
> > getting the estimates.
> >
> > The reason why I have so many x's, is that I am estimating a two-stage
> > procedure and I need all the coefficients of the first stage to
> > compute the Murphy-Topel standard errors.
> > For this reason, I end up having to estimate all the fixed effects as
> > dummy variables.
> >
> > Richard
> *
> *   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/
>


-- 
AbdelRahmen El Lahga
*
*   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