Please study the rw-FAQ. With a 2GB address space your chance of getting
a 1.5GB contiguous block is essentially zero.
On Tue, 2 Sep 2008, Hayes, Daniel wrote:
Dear all,
In my attempt to run the below modelling command in R 2.7.0 under windows XP
(4GB RAM with /3GB switch set) I receive the following error:
Error: cannot allocate vector of size 1.5 Gb
I have searched a bit and have tried adding: --max-mem-size=3071M to the
command line (when set to 3G I get the error that 3072M is too much)
I also run:
memory.size()
[1] 11.26125
memory.size(max=T)
[1] 13.4375
Modelling script:
model.females <- quote(gamlss(WAZ11~cs(sqrtage,df=12)+country,
sigma.formula=~cs(sqrtage,df=3)+country,
nu.formula=~cs(sqrtage,df=1), tau.formula=~cs(sqrtage,df=1),
data=females, family=BCPE, control=con))
fit.females <- eval(model.females)
the females (1,654KB) that is being modelled by the GAMLSS package contains
158,533 observations
I have further installed various memory optimization programs under XP but to
no avail.
I believe that I perhaps need to set the Vcells and Ncells but am not sure
which nor to what limits.
Any other help in maximizing my RAM usage in R would be great
I am quite a novice so please excuse any obvious mistakes or omissions.
Thank you in advance for your help
Dr. Daniel Hayes
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
--
Brian D. Ripley, [EMAIL PROTECTED]
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272866 (PA)
Oxford OX1 3TG, UK Fax: +44 1865 272595
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.