R help - Jun 2012 - load coda in BRugs to perfor diagnostics

Dear all,

I just wrote a script to have each of my three mcmc chins running on a
different computer core to improve computation speed. To do it I use the
function sfLapply from the package snowfall.
Before using parallell computation, I did my diagnostic analyses just after
the model updating, but now I have to save the coda before. 
Using the CODA package, it is possible to load the outputs in a mcmc.list to
perform some diagnostics but it doesn't work with functions from the BRugs
package such as samplesBgr. 
Can you explain what should I do to read coda files with BRugs ? 

Thanking you in advance

Guillaume

--
View this message in context:
http://r.789695.n4.nabble.com/load-coda-in-BRugs-to-perfor-diagnostics-tp4632420.html
Sent from the R help mailing list archive at Nabble.com.

On 05.06.2012 18:30, Guillaume2883 wrote:
> Dear all,
>
> I just wrote a script to have each of my three mcmc chins running on a
> different computer core to improve computation speed. To do it I use the
> function sfLapply from the package snowfall.
> Before using parallell computation, I did my diagnostic analyses just after
> the model updating, but now I have to save the coda before.
> Using the CODA package, it is possible to load the outputs in a mcmc.list
to
> perform some diagnostics but it doesn't work with functions from the
BRugs
> package such as samplesBgr.
> Can you explain what should I do to read coda files with BRugs ?
You cannot.

BRugs runs OpenBUGS in the background and is just an interface plus some 
sugar for OpenBUGS. Functions such as samplesBgr() get the data of the 
current sampling state from OpenBUGS.

Best,
Uwe Ligges

>
> Thanking you in advance
>
> Guillaume
>
> --
> View this message in context:
http://r.789695.n4.nabble.com/load-coda-in-BRugs-to-perfor-diagnostics-tp4632420.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.