----- Forwarded message from andrea cardini <[email protected]> -----
Date: Wed, 19 Mar 2014 05:02:44 -0400
From: andrea cardini <[email protected]>
Reply-To: andrea cardini <[email protected]>
Subject: Re: Sample size, hybrids, and R
To: [email protected]
Quick comments below, Sam. Sorry for the rush.
It's my teaching semester and have very little time.
At 03:38 19/03/2014, you wrote:
>----- Forwarded message from "Samuel F. Rizza"
><[email protected]> -----
>
>Date: Thu, 6 Mar 2014 15:50:42 -0800
>From: "Samuel F. Rizza" <[email protected]>
>Reply-To: [email protected]
>Subject: Sample size, hybrids, and R
>To: [email protected]
>
>Hi all,
>
>I am a graduate student looking at morphometrics
>and genetics of coastal cutthroat trout(CCT),
>steelhead trout(SH), and their hybrids(HY). Â I
>used 14 landmarks on 381 CCT, 182 SH, and 15 HY
>(these are putative species IDs recorded in
>field until genetics are determined). Â I am
>trying to determine if HY are morphologically
>different than CCT and/or SH and if so, how? Â I
>understand this may be hard with such a small HY sample size. Â
>
>1. Does the difference in sample sizes of CCT,
>SH, and HY alter the consensus shape effecting
>my results when comparing group differences in PCA and CVA?
a) N will affect accuracy of all parameter
estimates: group means, variances etc. (e.g.,
Cardini & Elton, 2007, Zoomorphol. - in my webpage).
b) Strong N heterogeneity likely will make all
potential issues in a DA/CVA worse (and its
assumptions hard to test). I fully agree that
testing the sensitivity of results when you have
a perfectly balanced design is a good idea.
However, then you'll have N=15 within each group
and 24 variables: overfitting is most likely.
Probably you'll have to consider some
dimensionality reduction and check how that too
might affect your results (e.g., Evin et al.,
2013 - my webpage - and refs therein for other
papers on DAs, its issues etc. including the
important ones I've mentioned in a previous
message - Mitteroecker and Bookstein, Klingenberg & Monteiro etc.).
Several years ago there was a PhD student doing
something similar on trouts in Italy. Her dataset
was also heterogeneous for N but her N was big (a
few thousands specimens, I think, although many less in the hybrid group).
I fear that the study has never been published
but Klingenberg gave her many good suggestions
she might be happy to share (she's in bcc, if her
email address is still the right one!).
Good luck
Andrea
>If so,Â
>2. Is R the best program to use to randomly
>sample an equal number of CCT from a TPS file?
>
>Thanks for all the posts, love the forum. Â Feel
>free to contact me directly with any papers or
>suggestions. Just getting into the field of
>morphometrics and enjoying its capabilities.
>
>Thanks,
>Sam Rizza
>Fisheries Graduate Student
>Humboldt State University, CA
><mailto:[email protected]>[email protected]
>Â
>
>
>
>----- End forwarded message -----
>
>
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, Centre for Anatomical and Human
Sciences, 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: [email protected], [email protected]
WEBPAGE: http://sites.google.com/site/hymsfme/drandreacardini
Summary of research interests at:
http://www.dscg.unimore.it/site/home/ricerca/aree-di-ricerca/evolution-taxonomy-and-forensics.html
FREE Yellow BOOK on Geometric Morphometrics:
http://www.italian-journal-of-mammalogy.it/issue/view/405
or full volume at:
http://www.italian-journal-of-mammalogy.it/public/journals/3/issue_241_complete_100.pdf
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 -----
