-------- Original Message -------- Subject: Re: help [morphoj Procrustes ANOVA -the mod] Date: Mon, 18 Jul 2011 16:24:45 -0400 From: Chris Klingenberg <[email protected]> Reply-To: [email protected] Organization: University of Manchester To: [email protected] Dear Julien With a Goodall F-value of 0.02 for the effect of individuals versus measurement error, I would suspect that a mistake during the data handling may have occurred. I'm also not quite sure about your study design -- you mention different observers, but there does not appear to be a corresponding effect in your output from the Procrustes ANOVA. Also, with 10 skulls and 43 3D landmarks per skull (back-calculated from the degrees of freedom), you may want to be cautious. For more information, see: Klingenberg, C. P., and G. S. McIntyre. 1998. Geometric morphometrics of developmental instability: analyzing patterns of fluctuating asymmetry with Procrustes methods. Evolution 52:1363–1375. http://www.flywings.org.uk/PDF%20files/Evol1998.pdf Klingenberg, C. P., M. Barluenga, and A. Meyer. 2002. Shape analysis of symmetric structures: quantifying variation among individuals and asymmetry. Evolution 56:1909–1920. http://www.flywings.org.uk/PDF%20files/Evol2002.pdf and the MorphoJ documentation at http://www.flywings.org.uk/MorphoJ_guide/frameset.htm?variation/procANOVA.htm Best wishes, Chris On 7/18/2011 7:01 PM, morphmet wrote:
[The original submission had embedded graphics that do not show up in the text-only version below. -the morphmet mod (dslice) ] -------- Original Message -------- Subject: help Date: Thu, 14 Jul 2011 18:19:59 -0400 From: Julien Sastre <[email protected]> To: [email protected] Hi, I'm a new to geometric morphometrics analysis and I'm working on cranial growth. In order to assess the reliability of the method, landmarks have been positionned twice by the same observer and twice by two differents observers. I would like to perform a Procrustes ANOVA in order to know if there is differences between the two measurement. For the reproductibility, I made a classifier "individual" where the same individuals are presents twice and a classifier "measure_serie" numbered 1 (=first measurement) or 2 (=second measurement). Then I perfomed a Procruste Anova And I obtained Procrustes ANOVA: Procrustes ANOVA ... Dataset: reproductibilité Classifiers used for the Procrustes ANOVA: Individuals: individual Error 1: measure_serie Centroid size: EffectSSMSdf F P (param.) Individual 2649,306645 294,367405 9 450,34 <.0001 Error 1 6,536558 0,653656 10 Shape, Procrustes ANOVA: EffectSSMSdf F P (param.) Pillai tr. P (param.) Individual 0,07606574 0,0000676140 1125 0,02 1,0000 Error 1 4,05229641 0,0032418371 1250 And I conclued that the two measurements are not significantly differents. Is the method valid? Any help is great. Thanks. Julien
-- *************************************************************** Christian Peter Klingenberg Faculty of Life Sciences The University of Manchester Michael Smith Building Oxford Road Manchester M13 9PT United Kingdom Telephone: +44 161 275 3899 Fax: +44 161 275 5082 E-mail: [email protected] Web: http://www.flywings.org.uk Skype: chris_klingenberg ***************************************************************
