Hi Will,

What you are observing is people falling into the "classic comic books"
version of statistical analyses, i.e., something is either "significant" or
"non-significant" based on some arbitrary cutoff of, say, alpha = 0.05.
Both of the statistics you mention are, of course, continuously valued,
though bounded at zero.  In general, you want to couple your consideration
of significance levels with looking at the value of the estimated
parameter, and also, I would suggest, compare your values with those
reported previously, e.g., as in in our large compilation in this original
paper:

Blomberg, S. P., T. Garland, Jr., and A. R. Ives. 2003. Testing for
phylogenetic signal in comparative data: behavioral traits are more labile.
Evolution 57:717–745.

As you wrote, attempting to construct confidence intervals with something
like simulations or parametric bootstrapping is also useful.

Cheers,
Ted


Theodore Garland, Jr., Distinguished Professor

Department of Evolution, Ecology, and Organismal Biology (EEOB)

University of California, Riverside

Riverside, CA 92521

Office Phone:  (951) 827-3524

Facsimile:  (951) 827-4286 (not confidential)

Email:  tgarl...@ucr.edu

http://www.biology.ucr.edu/people/faculty/Garland.html

http://scholar.google.com/citations?hl=en&user=iSSbrhwAAAAJ


Director, UCR Institute for the Development of
<http://idea.ucr.edu/>Educational
Applications <http://idea.ucr.edu/>


Editor in Chief, *Physiological and Biochemical Zoology
<http://www.press.uchicago.edu/ucp/journals/journal/pbz.html>*


Fail Lab: Episode One

*https://www.youtube.com/watch?v=c0msBWyTzU0
<https://www.youtube.com/watch?v=c0msBWyTzU0>*

On Mon, Oct 9, 2017 at 12:17 PM, William Gelnaw <wgel...@gmail.com> wrote:

> Hi Everyone,
>   I'm measuring phylogenetic signal in a morphometric dataset using Pagel's
> Lambda and Blomberg's K.  I tend to think of both of these as continuous
> values, but in reviewing the literature I've noticed that most authors
> treat phylogenetic signal as either there or not.  The way that the
> P-values are calculated, comparing the observed character distribution to
> that expected given no phylogenetic signal, also suggests a very binary way
> of looking at phylogenetic signal.  There are definitely some authors that
> treat K and Lambda as continuous, but they seem to be the exception.  Also,
> although parametric bootstrapping seems to be a good way to get a
> confidence interval for signal values, I've hardly seen it used.  I'm just
> wondering if there is a reason for strictly treating phylogenetic signal as
> just present or absent, or if I'm seeing a pattern that isn't really
> there.
>    Best regards,
>   Will
>
>         [[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-ph...@r-project.org/
>

        [[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