aydin wrote:
> ...as opposed to statistical significance.
>
> http://tinyurl.com/3anjuu -- Aydin  snailstales.blogspot.com

* In a case like this, you've got to wonder about subtle changes in the
way the measurements were taken. I've heard the tale told, of a student
of osteometric variation in birds, that when he took his many
measurements on a series of samples of skeletons, and then came back and
remeasured the first sample, there was no univariately significant
difference between any of the measurements, but a discriminant function
correctly identified most (maybe all) of them as being measured as the
first or last sample, showing that he'd somehow changed how the
measurements were judged in the course of measuring the intervening
samples.

I'd say that "biological significance" can occur only when you're
testing a hypothesis -- otherwise "p" is just a statement of how
different the samples are, and a hint about the kind of hypothesis you
might want to test on other samples or in other ways.

(I tried to leave this as a comment on the blog, but it didn't seem to
want to take it).

fred (newly resubscribed to CONCH-L after a lapse of years)
------------------------------------------------------------
             Bishops Mills Natural History Centre
           Frederick W. Schueler & Aleta Karstad
        RR#2 Bishops Mills, Ontario, Canada K0G 1T0
     on the Smiths Falls Limestone Plain 44* 52'N 75* 42'W
       (613)258-3107 <bckcdb at istar.ca> http://pinicola.ca
------------------------------------------------------------
subscribe to the Eastern Ontario Natural History list-serve at
http://mail.thenaturejournal.com/mailman/listinfo/naturelist_thenaturejournal.com
------------------------------------------------------------

----------------------------------------------------------------------
[log in to unmask] - a forum for informal discussions on molluscs
To leave this list, click on the following web link:
http://listserv.uga.edu/cgi-bin/wa?SUBED1=conch-l&A=1
Type your email address and name in the appropriate box and
click leave the list.
----------------------------------------------------------------------