Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: RE: Speeding up time series regressions on a multi-processor computer


From   "Peter Velte" <run-it@gmx.net>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: RE: Speeding up time series regressions on a multi-processor computer
Date   Mon, 05 Jul 2010 15:19:55 +0200

Tried your suggestion and it helped a bit. Yet, still the 8-core server is substantially slower than my single core laptop with Stata IC.

Isn't there any regression script, which can calculate multiple Newey-West-robust time series regressions simultaneously/parallely through matrix operations?

If I understand function mvreg correctly it does just this, but unfortunately cannot handle unbalanced panels and cannot estimate Newey-West standard errors. Anyone who knows an extension of mvreg?

Thanks for your help,
Peter


-------- Original-Nachricht --------
> Datum: Wed, 30 Jun 2010 19:34:20 +0200
> Von: "Martin Weiss" <martin.weiss1@gmx.de>
> An: statalist@hsphsun2.harvard.edu
> Betreff: st: RE: Speeding up time series regressions on a multi-processor computer

> 
> <>
> 
> You might want to open 8 instances of Stata, split the tasks accordingly,
> and -set processors 1- on each of them. You would have to aggregate the
> results later. Keep a -log- open on each one...
> 
> 
> HTH
> Martin
> 
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Peter Velte
> Sent: Mittwoch, 30. Juni 2010 18:39
> To: statalist@hsphsun2.harvard.edu
> Subject: st: Speeding up time series regressions on a multi-processor
> computer
> 
> Hi,
> 
> is there any way to compute multiple time series regressions on a
> multi-processor computer simultaneously?
> 
> The regressions are completely independent from each other, using
> Newey-West standard errors ("regress return rmrf smb hml mom, vce(robust)").
> 
> At the moment I perform a simple while-loop on the regressions, leading to
> mainly 1 core of 8 available being used.
> 
> Any solutions to that?
> 
> Thanks,
> Peter

-- 
GRATIS für alle GMX-Mitglieder: Die maxdome Movie-FLAT!
Jetzt freischalten unter http://portal.gmx.net/de/go/maxdome01
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   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   |   Site index