[R-sig-ME] random regression with MCMCglmm

[Jarrod Hadfield]

Hi Celine,

The most likely reason is that Cat or st2Food are not present in your  
data frame.  If this is not the case, then let me know and I'll take a  
more detailed look.

Cheers,

Jarrod


On 23 Jun 2009, at 16:07, Celine Teplitsky wrote:

> Dear all,
>
> I would like to fit a random regression using MCMCglmm. The problem  
> is I don't manage to include heterogeneous residual variance (when I  
> use just one residual variance the model is running). I have created  
> a factor (Cat) grouping the environments into 4 food qualities from  
> good to bad, so the model looks like:
> priorA<-list(G=list(G1=list(V=diag(2), n=2)),R=list(V=diag(4), n= 2))
>
> MCMCglmm(LD ~ Age+stFood , random=~us(1+st2Food):ID, rcov =  
> ~us(Cat):units, data=Data,prior=priorA, family =  
> c("gaussian"),nitt=120000, burnin=20000, thin=100)
>
> but I get this error message, and I really don't know how to fix the  
> problem:
>
> Error in `[.data.frame`(data, , components[[1]]) :
>  undefined columns selected
>
> Many thanks in advance for any help
>
> Celine
>
> -- 
>
> Celine Teplitsky
> Département Ecologie et Gestion de la Biodiversité UMR 7204
> Unité Conservation des Espèces, Restauration et Suivi des Populations
> Case Postale 51
> 55 rue Buffon 75005 Paris
>
> Webpage : http://www2.mnhn.fr/cersp/spip.php?rubrique96
> Fax : (33-1)-4079-3835
> Phone: (33-1)-4079-3443
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>


-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.