----- Forwarded message from al cardini -----
Date: Thu, 29 Nov 2012 04:56:01 -0500
From: al cardini
Reply-To: al cardini
Subject: Re: Problem with MorphoJ and discriminant function
To: morphmet@morphometrics.org
Dear Débora,
that's something that used to happen to me when I had many 3D
landmarks. However, I guess it was simply taking its time for doing
the resampling stats.
I've noticed that since I installed the latest version, the software
gets stuck every now and then (for instance, when saving a large
project). I am not sure if that's OK or there's some kind of issue
(possibly with java).
For the permutation test and discriminant analysis, I am now doing
those in R or in PAST using PCs of shape coordinates. If possible I
use all of them, and that's the same as using all shape coordinates,
or I select an appropriate number of the first PCs (enough for the
change in pairwise shape distances to be minimal).
This tends to work better, in my experience, and avoids some issues
I've noticed a few times using shape coordinates. With appropriate N,
results should be the same but if your N are small and/or
heterogeneous across groups, things might become less straightforward
(Evin et al., 2012, Journal of Archaeological Sciences, says something
about this and has refs).
For the visualization, especially with two groups, you could just do a
PCA on the mean shapes of those two groups. PC1 will account for 100%
of variance and you will be simply showing the mean shapes.
In terms of ordinations, if you want to do a scatterplot summarizing
group differences without distorting the spatial relationships in the
Procrustes shape space (see Klingenberg & Monteiro, 2005, Syst.
Biol.), you could also try the between group PCA (described in a few
recent papers including Mitteroecker & Bookstein, 2011, and Seetah et
al., 2012 - in my webpage with the full refs to the other papers I
mentioned). BG-PCA is now implemented in PAST.
Good luck.
Cheers
Andrea
On 29 November 2012 09:09, <morphmet_modera...@morphometrics.org> wrote:
>
> ----- Forwarded message from Débora Martínez -----
>
> Date: Wed, 28 Nov 2012 09:50:17 -0500
> From: Débora Martínez
> Reply-To: Débora Martínez
> Subject: Problem with MorphoJ and discriminant function
> To: Morphmet
>
> Hello,
>
> I think I have a problem with MorphoJ and the discriminant function option.
> When I try to perform this kind of analysis, my laptop takes a lot of time
> to do it and I was only comparing two groups between them and not all the
> pairwises. I have proved to perform the analyzes in another computers more
> potent than mine and it is the same, the program is always running but I
> cannot see the results. I also have proved with different MorphoJ versions
> and it is also the same. Anyone can help me?? Anyone know what happens or if
> I'm doing something wrong?
>
> Thanks in advance
> Débora
>
>
>
> ----- 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 -----
