-------- Original Message -------- Subject: Re: How to demonstrate the power of geometric morphometrics? Date: Thu, 31 Mar 2011 03:37:57 -0400 From: Göran Arnqvist <[email protected]> Reply-To: [email protected] Organization: Uppsala University To: [email protected] On 2011-03-30 23:37, morphmet wrote:
2) How come one way of doing the analysis is finding PCs that match what I put in whereas another way is finding mixed variations?
They shouldn't. Results should be identical, if "options" in the EFA are set equal. Any chance that you based the PCA of EFA coefficients on the correlation matrix (instead of the covariance matrix, which should be used) in one of the programs? I tend to to prefer to use Morpheus et al for EFA - it's great for this purpose. PCs from EFA are, in my experience, very efficient at picking up "perceived" and interpretable shape variation. /Göran -- ******************************************************************** Prof. Göran Arnqvist Animal Ecology Department of Ecology and Evolution Evolutionary Biology Centre University of Uppsala Norbyvägen 18d SE - 752 36 Uppsala Sweden Email: [email protected] Phone: +46-(0)18-471 2645 Cell phone: +46-(0)70-2935032 Fax: +46-(0)18-471 6484 NEW homepage with PDF reprints and more at: http://www.anst.uu.se/goarn789/index.html ********************************************************************
