[R-sig-eco] asymetric matrix - pairwise experiments

[Martin Weiser]

Dear list participants,

I would like to know your opinion on data analysis techniques
available for the experiment we performed.

We conducted an experiment with pairs of individuals, comming from 15
species. All species were combined, including same-species pairs,
all combinations in several (10) replicates (asymmetric matrix with ten
replicates per field). We want to link the outcome of the experiment
(response of each of the individuals) with (three) species traits.
(e.g. bigger species are more supressed by the smaller neighbours than
by the bigger ones) 

What we did (one of the variants): We took the response of each species
in each combination, and for the particular species, we sorted the
treatments (neighbour species) according to the response the treatment
elicited in the target species (e.g. level of supression). Then, we
correlated order of the treatments (neighbour species) with the order
according to the trait (e.g. size).
So we get 15 corr. coefs (one for each species) as a response norm, and
correlated these corr. coefs. with the species traits (e.g. size of
the species).

Well, I hope the approach is not plainly wrong, but at least it seems to
be not a very elegant one.

I would appreciate your suggestions.

With the best regards,
Martin Weiser  




-- 

------------------------------
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.