R help - Mar 2011 - JAGS/BUGS on gene expression data

Has anybody had issues running MCMC (either BUGS or JAGS) on data sets of
this magnitude (ie 30k x 20-30).  I've been trying to run a hierarchical
random effects model on expression data but R completely stalls out on jobs
run on 32bit R on our server (doesn't respond...then eventually crashes out
with an exception fault).  Would using 64bit R help with JAGS?  (As far as I
know there's only a 32bit build of BRugs so BUGS is out) Currently the
server doesn't have 64 bit JAGS installed but I've put in a request.  It
seems that compiling the model is what's crashing R at this point.

My last resort is to hardcode everything in C, but I'd like to avoid that.

--
View this message in context:
http://r.789695.n4.nabble.com/JAGS-BUGS-on-gene-expression-data-tp3354065p3354065.html
Sent from the R help mailing list archive at Nabble.com.

There are better alternatives for big data than to revert to C.

http://code.google.com/p/pymc/
http://github.com/armstrtw/CppBugs (still alpha)

-Whit


On Mon, Mar 14, 2011 at 11:06 AM, nblarson <nblarson at gmail.com>
wrote:
> Has anybody had issues running MCMC (either BUGS or JAGS) on data sets of
> this magnitude (ie 30k x 20-30). ?I've been trying to run a
hierarchical
> random effects model on expression data but R completely stalls out on jobs
> run on 32bit R on our server (doesn't respond...then eventually crashes
out
> with an exception fault). ?Would using 64bit R help with JAGS? ?(As far as
I
> know there's only a 32bit build of BRugs so BUGS is out) Currently the
> server doesn't have 64 bit JAGS installed but I've put in a
request. ?It
> seems that compiling the model is what's crashing R at this point.
>
> My last resort is to hardcode everything in C, but I'd like to avoid
that.
>
> --
> View this message in context:
http://r.789695.n4.nabble.com/JAGS-BUGS-on-gene-expression-data-tp3354065p3354065.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help at 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.
>