[R-sig-eco] Fwd: Fwd: how to calculate "axis variance" in metaMDS, pakage vegan?

[Jari Oksanen]

On 11/12/09 00:26 AM, "Jari Oksanen" <jari.oksanen at oulu.fi> wrote:

> On 10/12/09 23:03 PM, "gabriel singer" <gabriel.singer at univie.ac.at> wrote:
> 
>> A difference between two communities within a host could still exist and
>> could make perfect sense, too, when you regard "community" as a random
>> factor. Then "community" may introduce some extra variation (compared to
>> the within-community variation), experimentally seen interesting and
>> important, because the replication of communities makes sure you are not
>> pseudoreplicating. I am not sure however, how to declare the correct df
>> for the random factor in adonis in this case... anybody knows better than I?
> 
> There is no way.
> 
> Random factors can be only mimicked by stratified permutation, but they
> cannot be defined in adonis. It is only for fixed effect models.
> 
Howdy,

Just to make clearer what I mean: adonis() uses standard formula
interpretation, and you can have nested factors in adonis(). So the
following work, and both define the same model:

 adonis(dune ~ A1/Management, dune.env)
 adonis(dune ~ A1 + A1 %in% Management, dune.env)

You can also have full crossed interactions

  adonis(dune ~ A1*Management, dune.env)

However, you should not combine nesting within a factor and stratification
with the same factor. The stratification is supposed to mimic the same
effects that you may want to show by nesting, but in more "random" way. At
least you must think very carefully what you do, and be able to justify that
both to yourself and other people (like the referees). Further, you must
remember that adonis() uses sequential tests and the effect of nesting is
not shown in terms before nesting, like the main effects. This may not be
what you wanted to do. Most importantly, there is no real way of having
*random* effects in adonis(), which was intended as the main message of my
previous posting on this issue. They are all fixed effects.

Cheers, Jari Oksanen