Dear all, I would like to know when I use NMDS stead PCA or CA analyses? Up to I know, I use PCA (or PCoA) for condense the great part of vaciance on the firsts axis, and CA (or DCA) when I would like to identify the structure/composition of data inside a matrix.
But I have seem that nowadays many ecologists are using NMDS to dimension reduction on data matrices, and interpret the axis (1, 2 etc) like they do on CA or DCA. My question is if I can use the axis of NMDS output on regression like I can do when with PCA, PCoA, CA and/or DCA axis. What is the "stress" effect on the usage of NMDS axis on regression? Another question is if are there a good PDF text about MDS and NMDS available on the web. I know that on "vegan" library (Thanks Oksanen!!) there are same fuctions which deal with MDS, metaMDS. Are there other packages that also works with MDS/NMDS/isoMDS on R? What are the similarity/difference on them? All comments are very welcome! Kind regards, Miltinho Brazil ____________________________________________________________________________________ http://yahoo.com.br/oqueeuganhocomisso [[alternative HTML version deleted]] ______________________________________________ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.