Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: insufficient memory bootrstrap
From
Stas Kolenikov <[email protected]>
To
[email protected]
Subject
Re: st: insufficient memory bootrstrap
Date
Tue, 19 Jul 2011 09:49:10 -0500
There's been some discussion of related issues on the list, in that
the results keep accumulating in memory rather than being dropped...
although frankly I don't remember what the resolution was. This is
probably an unfortunate combination of the mechanics of -bootstrap-
and the details of implementation of whatever you are bootstrapping
(e.g., your estimation command produces a matrix or tempvar it does
not clear; or the -bootstrap- produces a matrix or a tempvar with each
iteration that it only clears in the end). Of course -drop-ping some
variables and observations should help, but unless you can write a
better program to -bootstrap-, that's likely all you can do as a user.
On Tue, Jul 19, 2011 at 8:13 AM, Jacqueline S. Zweig <[email protected]> wrote:
> Dear Satalist,
>
> I am running a quantile regression with 25 independent variables and
> bootstrapped standard errors. When I use 250 reps, I get the
> following error message:
>
> Bootstrap replications (250)
> ----+--- 1 ---+--- 2 ---+--- 3 ---+--- 4 ---+--- 5
> ..............................
> .................... 50
> .................................................. 100
> .................................................. 150
> .................................................. 200
> ..................................unable to restore data due to
> insufficient memory; try discard first
> unable to restore data due to insufficient memory; try discard first
> unable to restore data due to insufficient memory; try discard first
>
>
> Below is my memory allocation. I am using a cluster, so the program is
> able to run on multiple processors.
>
>
> Current memory allocation
>
> current memory usage
> settable value description (1M = 1024k)
> --------------------------------------------------------------------
> set maxvar 11000 max. variables allowed 3.935M
> set memory 15360M max. data space 15,360.000M
> set matsize 11000 max. RHS vars in models 924.080M
> -----------
> 16,288.015M
>
>
> Is there anything I can do to fix this?
>
>
> Thanks,
> Jackie
>
> *
> * 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/
>
--
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.
*
* 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/