[R-sig-eco] two nested conditioning factors in capscale()

[Martin Weiser]

Alicia Valdés píše v Čt 22. 05. 2014 v 15:47 +0200:
> Hi,
> 
> I am using the function capscale() in vegan to perform a partial
> distance-based RDA. I would like to use not one, but two conditioning
> factors, A and B, in order to remove their effects out of the analysis. B
> is nested in A. I don't know if this is possible, but I have tried with
> Condition(A/B) and the model works, but I am doubting if it is doing
> exactly what I want.
> 
> Thanks in advance for any help,
> 
> _______________________________________________
> R-sig-ecology mailing list
> R-sig-ecology at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-ecology

Hi Alicia,

if A and B are nested, I see no point in "removing the effect" of the
factor lower in hierarchy (as it is fully included in the other factor).
Just be sure you specify the strata in the randomisation test, if you
are going to use it.

Another option is just to generate new factor of as many levels as there
are A and B combinations and use this new variable for conditioning.

HTH,
Martin



-- 

------------------------------
Pokud je tento e-mail součástí obchodního jednání, Přírodovědecká fakulta 
Univerzity Karlovy v Praze:
a) si vyhrazuje právo jednání kdykoliv ukončit a to i bez uvedení důvodu,
b) stanovuje, že smlouva musí mít písemnou formu,
c) vylučuje přijetí nabídky s dodatkem či odchylkou,
d) stanovuje, že smlouva je uzavřena teprve výslovným dosažením shody na 
všech náležitostech smlouvy.