-------- Original Message --------
Subject: Re: discriminant function in MorphoJ
Date: Wed, 6 Jul 2011 17:15:11 -0400
From: [email protected]
To: [email protected]
CC: morphmet <[email protected]>
Dear community
I know this is not strictly inherent with the specific
problem of previous post. However.....about
Discriminant Analysis I found this paper illuminating
(suggested me by Dean Adams).
Mitterocker,P., and Bookstein, F. 2011. Linear
Discrimination, Ordination, and the Visualization
of Selection Gradients in Modern Morphometrics Evol
Biol (2011) 38:100114.
In particular look at Fig. 5. In absence of a number
of cases MUCH HIGHER (4 5 times) than the number of
variables (i.e. n°
landmarks*n°dimensions),Discriminant Analysis should
not be used. One can obtain comlpetely false group
separation.
Hope this helps
Best
Paolo
-------- Original Message --------
Subject: Re: discriminant function in MorphoJ
Date: Wed, 6 Jul 2011 12:09:55 -0400
From: Joseph Kunkel <[email protected]>
To: [email protected]
Daniella,
That is the very point of discriminant function
analysis. One develops
the functions using a set of data from individuals in
which you know the
sex definitively by some other criterion. Then you
use the discriminant
functions to apply to unknowns for which you want to
predict the sex.
Joe
On Jul 6, 2011, at 12:02 PM, morphmet wrote:
-------- Original Message --------
Subject: discriminant function in MorphoJ
Date: Tue, 5 Jul 2011 15:57:46 -0400
From: Daniela Sanfelice
<[email protected]>
To: [email protected]
Hello...
by the way, yet using MorphoJ...
If I have a "good" discriminant function result for
sex, can I try to
apply it to individuals that I don´t know the sex
to "estimate" sex in it?
Thank you very much, cheers, Daniela Sanfelice.
-·. .· ·. .><((((º>·. .· ·. .><((((º>·. .· ·.
.><((((º> .··.· >=-
=º}}}}}><
Joseph G. Kunkel, Professor
Biology Department
University of Massachusetts Amherst
Amherst MA 01003
http://www.bio.umass.edu/biology/kunkel/
