Region by Environment models...

The model I used in the previous email was pretty a basic compound
symmetry model.
 
a.asr <- asreml(fixed = gyp ~ Env,
        random = ~Genotype + Region:Genotype + Region:Env:Genotype,
        rcov = ~units)
 
I would like to use better corh or fa structures in this analysis.
Ideally, these would be fitted to the entire dataset and then the data
predicted by Region somehow...
For example, I know that a corh model fits much better to the entire set
of environments in this dataset:
 
a.asr <- asreml(fixed = gyp ~ Env,
        random = ~corh(Env):Genotype,
        rcov = ~units)
 
However, I would like to be able to predict at each region, so can I
somehow nest the corh model within region, or will I have to run these
separately?
 
a.asr <- asreml(fixed = gyp ~ Env,
        random = ~diag(Region):corh(Env):Genotype,
        rcov = ~units)
 
or perhaps:
 
 a.asr <- asreml(fixed = gyp ~ Env,
        random = ~at(Region, 1):corh(Env):Genotype + at(Region,
2):corh(Env):Genotype,
        rcov = ~units)
 
The problem with these models appears to be that I would need to fit the
corh only to the Envs that occur within each Region. Does that mean I
need to have two new Env factors where they are declared NA for the
regions where they do not occur?
Received on Fri Feb 26 2008 - 10:55:54 EST