[R-sig-eco] Pushing the PCNM x adonis issue further

[afsouza at unisinos.br]

Dear friends,

   I would like to ask your opinion on the use of PCNM results,
continuing a discussion that recently took place at R-sig-eco between
Jari Oksanen and Kevin McCluney.

   When it was recommended not to mix adonis and pcnm (Nov 06, 2010)
Jari
was referring to the internal steps needed to extract the final pcnm
vectors, not to the posterior use of these final vectors as a single
covariate block in adonis in the as.matrix form, wright?

   Because the use of as.matrix(pcnm) would let us control for (at
least try to) spatial structure when testing specific effects of
environmental factos on species abundances, while all other species
variance partitioning procedures (varpart, through rda-cca) try to
identify the total variance attibutable to space, environmental factors
(as a group, and not specified in an MANOVA-like design) and env factos
spatially structured, what is complimentary but not the same.

   Best whishes,

   Alexandre

Dr. Alexandre F. Souza 
Programa de Pós-Graduação em Biologia: Diversidade e Manejo da Vida
Silvestre
Universidade do Vale do Rio dos Sinos (UNISINOS)
Av. UNISINOS 950 - C.P. 275, São Leopoldo 93022-000, RS  - Brasil
Telefone: (051)3590-8477 ramal 1263
Skype: alexfadigas
afsouza at unisinos.br
http://www.unisinos.br/laboratorios/lecopop