----- Forwarded message from morphmet_modera...@morphometrics.org -----
Date: Mon, 26 Nov 2012 23:19:09 -0800
From: morphmet_modera...@morphometrics.org
Reply-To: morphmet_modera...@morphometrics.org
Subject: Re: Do you need to know size for Procrustes superimposition?
To: morphmet@morphometrics.org
----- Forwarded message from al cardini -----
Date: Mon, 26 Nov 2012 05:46:18 -0500
From: al cardini
Reply-To: al cardini
Subject: Re: Do you need to know size for Procrustes superimposition?
To: morphmet@morphometrics.org
Dear Patrick,
I made pretty similar comments in my reply to your message.
Just a quick comment on allometry. I prefer to say that one holds the
effect of allometry constant when comparing groups if we are talking
about the MANCOVA model for 'controlling' for allometry. On the
assumptions of this method, I'd carefully read the dedicated section
in the Green Book (Zelditch et al., 2004 - but check if a new edition
is already out) and maybe also the help file of TPSRegr (test for
slopes and intercepts). Also, on whether allometry is really 'removed'
using ANCOVAs, I would suggest you to read Gould's seminal paper on
this topic.
Good luck.
Cheers
Andrea
PS
Be also careful with what 'residuals' mean in this context especially
when you have multiple groups.
On 26 November 2012 01:52, <morphmet_modera...@morphometrics.org> wrote:
>
> ----- Forwarded message from Soledad Esteban -----
>
> Date: Sat, 24 Nov 2012 03:05:55 -0500
> From: Soledad Esteban
> Reply-To: Soledad Esteban
> Subject: Re: Do you need to know size for Procrustes superimposition?
> To: morphmet@morphometrics.org
>
> Dear Patrick:
>
> You do not need to know the real size of the individuals to do a Procrustes
> superimposition, it just would compute the centroid size from the relative
> picture size and scale all the individuals to the same centroid size. With
> this you remove differences due to differences in scaling when taking the
> pictures, but if there are some differences in shape related to differences
> in size (allometry) they would be present in your sample after superimpose
> them despite your specimens are fitted to the same size. The only way of get
> ride of allometric scaling is knowing the real size of each specimen (thus
> centroid size really represents the size of each specimen). In biology
> allometry many times is quite an important factor, and usually it is better
> to get the real size information whenever it is possible and check for the
> importance of allometry on them. Indeed, depending on your study reviewers
> may ask you to control for allometric factors, i.e.: are the shape
> differences you get due to differences in size? And if yes, you may want to
> remove the allometric effect working with the residuals of a regression
> between shape and centroid size (or log centroid size). Thus, the real size
> is not important for GPA, but it may be for your biological conclusions.
> Therefore it is up to you wether you take the risk and ignore the size
> factor which you may will need later, but no need of it just for GPA.
>
> I hope this helps!
>
> Best regards
> Sole
>
> Soledad De Esteban Trivigno
> Area de Paleobiología
> Institut Català de Paleontologia
> Edifici ICP, Campus de la UAB
> 08193 Cerdanyola del Vallès
> Barcelona. Spain
> www.icp.cat
>
> ________________________________
> -----Mensaje original-----
> De: morphmet_modera...@morphometrics.org
> A: morphmet@morphometrics.org
> Fecha: 11/24/12 07:38
> Asunto: Do you need to know size for Procrustes superimposition?
>
>
> ----- Forwarded message from Patrick Kennedy -----
>
> Date: Wed, 21 Nov 2012 21:19:26 -0500
> From: Patrick Kennedy
> Reply-To: Patrick Kennedy
> Subject: Do you need to know size for Procrustes superimposition?
> To: "morphmet@morphometrics.org"
>
>
>
> Hi,
>
> I'm completely new to morphometrics, so sorry if this question seems a bit
> basic/obvious to those in the know!
>
> I have a roughly 400 individuals, which are divided into nine different
> groups, and I want to find out whether these different groups have different
> mean shapes. I'm going to use MANOVA here. But to get to that point, I'll
> need, of course, to do Procrustes superimposition. Each group was
> photographed at a different time, so the scale differs each time. I have a
> reference to scale each group to, but it would be a long and tedious process
> to go through each individual setting the scale. Is this necessary? Could I
> just run the Procrustes superimposition as it is with individuals
> photographed at different distances?
>
> In other words (and sorry if this seems a stupid question), do I need to
> tell the software the actual/relative sizes of the specimens in order to do
> the superimposition? I can't really see why you would need to (though I am a
> humble undergraduate just beginning here, so I thought I would check).
>
> Many thanks to anyone who can advise.
>
> Patrick
> patrick.kenn...@bnc.ox.ac.uk
>
>
>
>
>
>
> ----- End forwarded message -----
>
>
>
>
>
> ----- End forwarded message -----
>
>
>
--
NO DOCX, XLSX AND PPTX, PLEASE!!!
COAUTHORS AND CONTRIBUTORS, PLEASE, FOR SHARING FILES, CONVERT THEM IN
DOC, XLS (UNLESS LONGER THAN 256 COLUMNS) AND PPT
Dr. Andrea Cardini
Researcher in Animal Biology
Dipartimento di Scienze Chimiche e Geologiche, Università di Modena e
Reggio Emilia, l.go S. Eufemia 19, 41121 Modena, Italy
Honorary Fellow
Functional Morphology and Evolution Unit, Hull York Medical School
University of Hull, Cottingham Road, Hull, HU6 7RX, UK
University of York, Heslington, York YO10 5DD, UK
Adjunct Associate Professor
Centre for Forensic Science , The University of Western Australia
35 Stirling Highway, Crawley WA 6009, Australia
E-mail address: alcard...@gmail.com, andrea.card...@unimore.it,
andrea.card...@hyms.ac.uk, andrea.card...@uwa.edu.au
Webpage: http://sites.google.com/site/hymsfme/drandreacardini
Datasets:
http://ads.ahds.ac.uk/catalogue/archive/cerco_lt_2007/overview.cfm#metadata
Editorial board for:
Zoomorphology:
http://www.springer.com/life+sciences/animal+sciences/journal/435
Journal of Zoological Systematics and Evolutionary Research:
http://www.wiley.com/bw/journal.asp?ref=0947-5745&site=1
Hystrix, the Italian Journal of Mammalogy:
http://www.italian-journal-of-mammalogy.it/
----- End forwarded message -----
----- End forwarded message -----
