Dear morphometricians, I've got a few issues on which I would greatly appreciate your advice. I thank you very much, in advance, for your help.
References, first. 1a) I am looking for papers on statistical comparisons of shape and genetic divergence. I am especially interested in how to test whether morphological divergence in a lineage is larger than expected based on genetic (neutral?) divergence. 1b) I'd like to read more on how to build confidence ellipses around sample mean shapes in PCAs. If I remember well, there were at least a couple of papers by Brasilian colleagues. I would greatly appreciate to have those and other references. Permutation tests. 2) A practical example. I've got two samples and I want to test differences in mean shapes using permutation tests. However, sample size is very different (say, sample A is 10 specimens and sample B 200). What is the consequence (if any) of such an unequal sample size on the test? ... Loss of statistical power??? Is this something I can get around by using random subsets of 10 specimens from sample B to do the permutation test? Software. 3) Does anybody have experience with running Morpheus on a Linux machine? I gave it a try in a computer lab but we did not make it. Also, I was wondering whether there's a way to run NTSYSpc on Linux. I cannot access the website now but I'll check later whether there's anything about this or even a Linux version of the program. Once more, thanks a lot for your always helpful advice. All the best Andrea Dr. Andrea Cardini Lecturer in Biology Museo di Paleobiologia e dell'Orto Botanico Universitá di Modena e Reggio Emilia via Università 4, 41100, Modena, Italy tel: 0039 059 2056532 fax: 0039 059 2056535 & Hull York Medical School The University of York, Heslington, York YO10 5DD, UK E-mail address: [EMAIL PROTECTED], [EMAIL PROTECTED], [EMAIL PROTECTED] http://www.york.ac.uk/res/fme/people/andrea.htm -- Replies will be sent to the list. For more information visit http://www.morphometrics.org
