[ADMB Users] Missing mcmc results

W Robert Long W.R.Long at leeds.ac.uk
Wed Jan 16 00:04:46 PST 2013


Haha. I knew that. How silly. Thanks a lot !!

On 16/01/2013 02:59, Torbjørn Ergon wrote:
> The head function gives you the top rows of whatever you put inside...
>
> Sent from my iPhone
>
> Den 15. jan. 2013 kl. 22:29 skrev W Robert Long <W.R.Long at leeds.ac.uk>:
>
>> Hi all
>>
>> I'm not sure if this is a problem with glmmabmb or the coda package, or (most likely) my code. I ran this model:
>>
>> fit1.mcmc <- glmmadmb(Y ~ time*X1 + time*X2 + ( 1| Subject), data=final, family="nbinom2", zeroInflation=TRUE,
>>          mcmc=TRUE,mcmc.opts=mcmcControl(mcmc=10000))
>>
>> and summary(zi1.mcmc) gave me the estimates I was expecting, that is:
>>
>>                           Estimate Std. Error z value Pr(>|z|)
>> (Intercept)               .......
>> time                     ......
>> X1                    ......
>> X2                    ......
>> time:X1                    ......
>> time:X2                     ......
>>
>> However, when running head(HPDinterval(as.mcmc(fit1.mcmc$mcmc))) I got
>>
>>                                lower      upper
>> pz                       ...........       ...........
>> (Intercept)           ...........       ...........
>> time                      ...........       ...........
>> X1                     ...........       ...........
>> X2                     ...........       ...........
>> time:X1         ...........       ...........
>>
>> The interval for time:X2 is absent.
>>
>> Am I missing something  (excuse the pun) ?
>>
>> Thanks
>> WRL
>>
>>
>>
>>
>>
>> _______________________________________________
>> Users mailing list
>> Users at admb-project.org
>> http://lists.admb-project.org/mailman/listinfo/users




More information about the Users mailing list