[R-sig-eco] permutest.cca and means seperation?

[Jari Oksanen]

On Wed, 2011-01-19 at 22:23 +0200, Wilson, Michael E wrote:
> Hi,
> With a CCA object such as outputed by capscale, I see that it is
> possible to calculate significance on a class factor with
> permutest.cca.
> 
> However, with multiple levels of a factor, is there a means separation
> technique for pairwise comparisons like permutest.betadisper but
> instead designed to use on centroids identified in a CCA object?

Michael,

This is not possible in permutest.cca (like you already noticed: I guess
you'd done this if it was possible). There really is some very clever
code in permutest.betadisper (fine Gav!), that can give  you pairwise
comparisons, but such a facility is not easily built in permutest.cca:
in betadisper() you're allowed to have only one grouping factor whereas
in caspcale/cca/rda you can have any formula which may or may not
include one or several factors that could be considered for pairwise
comparisons. A separate set of tools is needed for pairwise comparison
in this context, and we do not provide those tools (but contributions
are welcome).

Cheers, Jari Oksanen