On Mon, 2 Apr 2012, Xiaobo Gu wrote:
You would need do compile your own copy of R and increase the stack
size,
Can we do this at runtime?
That depends on your unstated OS. Uwe gave you an answer for Windows.
On many other OSes, the stack size is set up by the OS when the
process is started, and your OS documentation will tell you how to
increase it.
You need at least 76252 obs and that means the design matrix needs > 46
Gbyte! Hence a sensible calculation is not really possible unless you
have really big machines around.
We do have big machines, but we don't have more obs for this data, so we will
revise the algorithm to try less combinations data set size.
He didn't say 'big machine'! I doubt it you could do anything useful
with less than 512GB RAM.
But more seriously, fitting a GLM (this message gives no context, but
I think that was the task) is a O(p^3) calculation, so you would also
need a great deal of patience.
Regards,
Xiaobo Gu
______________________________________________
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, rip...@stats.ox.ac.uk
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.
