Damien Esquerre asked:

> What do you think would be the most appropriate way to deal with this 
> situation then, if you are interested in environmental effects on shape?


Issues of heterogeneity of regression parameters are relevant, but
there is one more issue that also needs attention.  That is, that
individual species should not be treated as independent, identically
distributed.  One needs to integrate such an analysis into a
phylogenetic comparative method.   Doing a regression across species
to remove a size effect is incorrect unless done taking the phylogeny
into account.  In addition, one should not assume that an
environmental effect has all of its influence in the most recent
generations.  Ideally, we would also want to allow for the environment
of the past to have had effects on the species, effects that have
partially persisted until today.

That raises the uncomfortable issue of how one models the change of
the environment along the tree.  We could have it too change by
Brownian Motion, but this seems arbitrary when applied to some aspect
of the physical environment, such as mean annual temperature.  It's
clearly a difficult problem.

J.F.
----
Joe Felsenstein         [email protected]
 Department of Genome Sciences and Department of Biology,
 University of Washington, Box 355065, Seattle, WA 98195-5065 USA

-- 
You received this message because you are subscribed to the Google Groups 
"Morphmet" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To view this discussion on the web visit 
https://groups.google.com/d/msgid/morphmet2/CABXfcPFLT5p4q59Su-Ag3p4G8EGSSJozKQxr6pv%2BE8gD0bLrSA%40mail.gmail.com.

Reply via email to