Hi Carmelo,

thank you so much for the suggestions. =)

All the best
Ting-Wen


--
Ting-Wen Chen
J.F. Blumenbach Institute of Zoology and Anthropology
Georg August University Goettingen
Berliner Str. 28
D-37073 Goettingen, Germany
Tel: +49-55139-10943

r-sig-phylo-requ...@r-project.org<mailto:r-sig-phylo-requ...@r-project.org> 於 
2016年12月16日 19:00 寫道:

Message: 5
Date: Fri, 16 Dec 2016 05:02:23 +0100
From: Carmelo Fruciano <c.fruci...@unict.it<mailto:c.fruci...@unict.it>>
To: r-sig-phylo@r-project.org<mailto:r-sig-phylo@r-project.org>
Subject: Re: [R-sig-phylo] bonferroni corrections in Blomberg's K and
Pagel's lambda
Message-ID: 
<20161216050223.47442dfb1b3g9...@webmail.unict.it<mailto:20161216050223.47442dfb1b3g9...@webmail.unict.it>>
Content-Type: text/plain; charset=UTF-8; DelSp="Yes"; format="flowed"

Hi Ting-Wen,
as Ted pointed out, if and how one has to correct for multiple tests
is a huge topic. Perhaps looking at the literature and making your own
opinion on this matter would be the best choice (for example, Perneger
1998 - British Medical Journal and Garcia 2004 - Oikos, present two
different points of view in a very accessible way).

A few extra points:
- There are other methods that are generally less conservative than
the Holm procedure ("Sequential Bonferroni"); these include the
Benjamini-Hochberg procedure (Benjamini & Hochberg 1995 - Journal of
the Royal Statistical Society; see also Benjamini & Yekutieli 2001 -
The Annals of Statistics) and other more recent procedures (such as
Carvajal-Rodriguez & de Una-Alvarez 2011 - Plos One); most of these
are worth checking out, making your opinion on them and, possibly,
using them (most of them have R implementations)

- If your dataset is multidimensional/multivariate in nature, you
might want to consider using multivariate approaches for estimating
and testing for phylogenetic signal (e.g., Adams 2014 - Systematic
Biology), rather than many univariate tests

- If your dataset/hypothesis is multivariate in nature, testing
individual PCs separately might be a poor choice (especially for PCs
of order higher than 1), if it is not multivariate in nature, there
might be no reason to use PCA

I hope this is of some help.
Best,
Carmelo



--
Carmelo Fruciano
Postdoctoral Fellow - Queensland University of Technology - Brisbane,
Australia
Honorary Fellow - University of Catania - Catania, Italy
e-mail c.fruci...@unict.it<mailto:c.fruci...@unict.it>
http://www.fruciano.it/research/


        [[alternative HTML version deleted]]

_______________________________________________
R-sig-phylo mailing list - R-sig-phylo@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-phylo
Searchable archive at http://www.mail-archive.com/r-sig-phylo@r-project.org/

Reply via email to