Hello, I have a dataset with 2000 species and multiple columns of colour proportion data. I want to test for differences in how certain groups, for example species living in one place versus another (various discreet independent variables), may separate in colour space based on presence absence and proportion of various colours. I do have multiple structural zeroes in the data. >From what I have gathered so far is that I need to add a small value to the >zeroes and also ILR transform my data to use it for PCA or NMDS. I want to >conduct a phylogenetic PERMANOVA with all the variables included and also >visualise this. Has anyone had any similar experience and can shed light on >what might be the best strategy?
Thank you Udita Bansal PhD Candidate Dept. of Ecology and Evolutinary Biology Cornell University _______________________________________________ R-sig-phylo mailing list - [email protected] https://stat.ethz.ch/mailman/listinfo/r-sig-phylo Searchable archive at http://www.mail-archive.com/[email protected]/
