[S] Memory problem during Gibbs sampling

G.J.A.Fox (foxj@edte.utwente.nl)
Mon, 18 May 1998 14:37:06 mez-2


I am dealing with large matrices and calcalute them (in
seperate functions) each iteration. After 1500 hundred iterations,
memory problems starts to occur. Restarting S-Plus gives me room for
another 1500 hundred. But I need 100000 iterations. Is it possble to
make more space (in a function environment) by removing variables?

Kerrie Paige (Date: Thu, 14 May 1998 08:04:47 -0700 ) has exactly
the same problem, I think.
It's going fine until the dynamic memory is full.

Thanks very much in advance.

Jean-Paul Fox.
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news