[R] Retrieving samples when ussing BRugs.

[Uwe Ligges]

On 14.12.2011 10:44, Thiago Guerrera wrote:
> Hi Sacha,
>
> I was referring to the BRugs package, where I usually proceed as follows:
>
> result = BRugsFit (...)
>
> param_samples = samplesSample("param")    (1)
>
> But (1) takes a long time for big chains. So my question was specific to
> BRugs, if there an alternative way to get the samples.

Short answer: No.
Long answer: Well, samplesHistory(..., plot=FALSE) may be more 
convenient for several parameters at once, but it uses samplesSample 
internally, that means: no.

Best,
Uwe Ligges




> openbugs() mentioned by you seems to be from R2WinBUGS that I have never
> used. I'll try that. Thanks for the suggestion.
>
> Best,
> Thiago
>
> On Fri, Dec 9, 2011 at 4:34 PM, Sacha Epskamp<sacha.epskamp at gmail.com>wrote:
>
>> If you obtain an output object with openbugs(), e.g.:
>>
>> samples<- openbugs( ... )
>>
>> Then this is a list with all the parameters and samples. See
>> names(samples). You can obtain the samples in a list with:
>>
>> samples[['sims.list']]
>>
>> Is this what you mean?
>>
>> On Fri, Dec 9, 2011 at 2:00 PM, Thiago Guerrera<thigm85 at gmail.com>  wrote:
>>> Hello R users,
>>>
>>> I have used the R package BRugs in some applications but one thing that
>>> annoy me is the functions to retrieve samples ("samplesSample") or
>> summary
>>> statistics ("samplesStats"). They take a really long time to return the
>>> values if the size of the chains in question is moderate, for example
>>> 10.000 samples. Does this happens with every one or there is a better way
>>> to obtain such values?
>>>
>>> Best
>>> --
>>> Thiago Guerrera.
>>>
>>>         [[alternative HTML version deleted]]
>>>
>>> ______________________________________________
>>> 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.
>>
>
>
>