[R-sig-ME] mixed manova?

[Jarrod Hadfield]

Hi,

If there is no natural ordering to the habitats you could use a  
multinomial mixed model, if there is you could use an ordinal mixed  
model. There are various libraries that have functions for fitting  
such models, for example mlogit, mixcat, ordinal & MCMCglmm. It might  
prove tricky with small samples sizes particularly if the number of  
observations per individual is small.

Cheers,

Jarrod

Quoting Sarah Jamieson <sarah.emily.jamieson at gmail.com> on Wed, 2 Jan  
2013 17:16:38 +1300:

> Hi.
>
> I am trying to determine whether habitat usage in birds varies between sex
> (male/female) or among seasons (summer, autumn, winter, spring).  I tracked
> 40 individual birds but my success locating each bird each season varied
> (e.g., in summer I only have data for 33 birds, while in winter I have data
> for all 40).
>
> I think I need to run a mixed manova model      habitat1 habitat2 habitat3
> = sex + season + sex*season + birdID  (birdID as the random factor)
>
> I am VERY new to R and have been flailing for 2 days trying to figure this
> out.  Can anyone help me with codes?
>
> Sarah
>
> 	[[alternative HTML version deleted]]
>
> _______________________________________________
> 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.