R help - May 2005 - memory and step()

Hi there,

I'm trying to perform a step(), using variables from a data set with 32.000
observations. The upper model is not so long  - (x1 + x2 + x3)^2 - where x1...x3
are the explanatory variables. Yet, I got a memory problem when performing it.
The message is the following:

Error: cannot allocate vector of size 26859 Kb
In addition: Warning messages:
1: Reached total allocation of 246Mb: see help(memory.size) 
2: Reached total allocation of 246Mb: see help(memory.size) 

I tried to see "help(memory.size)", but that was not too enlightening.
As I am not familiar with these memory problems, I am asking for your help. What
should I do so that I can perform this (and many others) step( )? I am under
Windows XP, using a P4 2.00 GHz with 256 Mb of RAM.

Thank you.
Dimitri
	[[alternative HTML version deleted]]

Dimitri Joe wrote:
> Hi there,
> 
> I'm trying to perform a step(), using variables from a data set with
32.000 observations. The upper model is not so long  - (x1 + x2 + x3)^2 - where
x1...x3 are the explanatory variables. Yet, I got a memory problem when
performing it. The message is the following:
> 
> Error: cannot allocate vector of size 26859 Kb
> In addition: Warning messages:
> 1: Reached total allocation of 246Mb: see help(memory.size) 
> 2: Reached total allocation of 246Mb: see help(memory.size) 
> 
> I tried to see "help(memory.size)", but that was not too
enlightening. As I am not familiar with these memory problems, I am asking for
your help. What should I do so that I can perform this (and many others) step(
)? I am under Windows XP, using a P4 2.00 GHz with 256 Mb of RAM.
memory.limit(512) will give you 512 Mb, if your system has enough swap 
space, BUT it will slow down dramatically!

See also the more detailed help page ?Memory.

My recommendation is: Buy a 512 Mb module for a few $, 256Mb is really 
not much these days.
Hmm, my 4.5 year old laptop already has 256Mb (cannot be increased - and 
this is the only point why I am looking fo a new one).

Uwe Ligges

> Thank you.
> Dimitri
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html