[R-sig-eco] ordination with categorical variables
Paolo Ruzza
paolo.ruzza77 at gmail.com
Thu Sep 8 23:39:21 CEST 2011
Dear all,
Apologies in advance for the total beginner's question. I would like
to perform a simple ordination on a dataset of species traits contaning
only categorical variables. My aim is to identify the relative niche position
of each species (possibly in the lowest number of dimensions).
I am tempted to perform a Principal coordinate analysis with a distance
distance matrix created with the gower dissimilarity coefficient. I have,
however, read that it is also possible to use other ordination methods such
as multiple correspondence analysis which seems to be specifically designed
for categorical variables. What is the best method? Which one should I choose?
Any help would be greatly appreciated!
Cheers
Paolo
--
Roma
Italy
More information about the R-sig-ecology
mailing list