Datum: Mon, 19 Dec 2011 12:16:33 +0000
Von: Andrew Crowe <Andrew.Crowe at fera.gsi.gov.uk>
An: "r-sig-mixed-models at r-project.org" <r-sig-mixed-models at r-project.org>
Betreff: Re: [R-sig-ME] problems with allocate memory with lme4 package
Paul
While I'm not an expert on the lmer function you might want to try the
following:
1) Check that you have a 64 bit install of R/lmer (not just 32 bit running
on a 64 bit system)
2) Try extending the memory using memory.limit()
3) Even with a complex model, 3 million rows is quite a lot of data.
Could this be reduced by subsampling and then using the 'removed' data for
validation of the model?
Regards
Andrew
Dr Andrew Crowe
Senior Land Use Change Scientist
Food and Environment Research Agency
Sand Hutton
York
UK
Email. Andrew.Crowe at fera.gsi.gov.uk
-----Original Message-----
From: r-sig-mixed-models-bounces at r-project.org
[mailto:r-sig-mixed-models-bounces at r-project.org] On Behalf Of cumuluss at web.de
Sent: 19 December 2011 11:39
To: r-sig-mixed-models at r-project.org
Subject: [R-sig-ME] problems with allocate memory with lme4 package
Hi to everyone,
?
I have been trying to fit with lmer function a glmm with a binomial error
structure. My model is a little bit complex. I have 8 continuous predictor
variables one of them as nonlinear term, 5 categorical predictor variables
with some three-way interactions between them. Additional I have 3 random
effects and one offset variable in the model. Number of obs is greater than
3million.
I?m working with the latest version of R 2.14.0 on a 64 bit windows
system with 8Gb ram.
Everything I tried (reducing model complexity, different 64bit PC with
even more memory) nothing leads to a fitted model, always the Error occurs:
cannot allocate vector of size 2GB.
Is there anything I can do? I would be very grateful for any commentary.
Paul T.