----- Forwarded message from [email protected] ----- Date: Tue, 01 Apr 2014 19:24:59 -0700 From: [email protected] Reply-To: [email protected] Subject: RE: Group differences To: [email protected]
----- Forwarded message from "F. James Rohlf" <[email protected]> ----- Date: Fri, 21 Mar 2014 19:09:49 -0400 From: "F. James Rohlf" <[email protected]> Reply-To: [email protected] Subject: RE: Group differences To: [email protected] The overall significance test in a CVA and a MANOVA are identical so they must give the same results for the same data. The purpose of the CVA is just to perform the extra step of providing an ordination of differences among groups relative to within-group variation. If you obtain different P-values then there is some problem such as using a different transformation of the original Procrustes aligned coordinates. They should both use the coordinates projected onto the tangent space. Perhaps for one of these analyses you used only a few PCs from this space? - - - - - - - - - - - - - - - - - - - - - - - - - - - - - F. James Rohlf, Distinguished Professor, Emeritus, Stony Brook University The much revised 4th editions of Biometry and Statistical Tables are now available: http://www.whfreeman.com/Catalog/product/biometry-fourthedition-sokal http://www.whfreeman.com/Catalog/product/statisticaltables-fourthedition-rohlf > -----Original Message----- > From: [email protected] > [mailto:[email protected]] > Sent: Friday, March 21, 2014 12:45 PM > To: [email protected] > Subject: Group differences > > > ----- Forwarded message from [email protected] ----- > > Date: Wed, 19 Mar 2014 22:16:24 -0700 > From: [email protected] > Reply-To: [email protected] > Subject: Group differences > To: [email protected] > > ----- Forwarded message from Patrick Arnold <[email protected]> ----- > > Date: Mon, 10 Mar 2014 08:59:14 -0400 > From: Patrick Arnold <[email protected]> > Reply-To: Patrick Arnold <[email protected]> > Subject: Group differences > To: [email protected] > > Dear morphometrics, > > my data contains 5 a priori determined groups. I did CVA in MorphoJ but I know > CVA not necessarily reveals significant groups. Thus, I want to verify my > groups > statistically. Manova with CVs in Past reveal significant groups, comparison > between groups in MorphoJ and Past, too. But, if I only use Procrusted > coordinates or PCs, Manova in Past says there are no significant different > groups. What do theses results say about my groups. Is significance with CVs > in > Manova enough to say that the 5 groups are really different in shape?? > > Patrick Arnold > > Institut für Spezielle Zoologie und Evolutionsbiologie mit Phyletischem Museum > Friedrich-Schiller-Universität Jena Germany > > ---------------------------------------------------------------- > This message was sent through https://webmail.uni-jena.de > > ----- End forwarded message ----- > > ----- End forwarded message ----- ----- End forwarded message ----- ----- End forwarded message -----
