[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Subject Index][Author Index]
Re: My apologies, but... physiology revisited
From: "Mickey P. Rowe" <email@example.com>
> I don't think Stan could possibly have read (or at least remembered)
> the paper and still have written the above.
You lost some of the context: what was claimed is that only four *birds*
were included in the analysis.
> I expect better of you guys. I have the paper in front of me now,
> and I invite Stan to look at its Figure 3. There are two regression
> lines here (much as you might see in a discussion of Harry Jerison's
> "EQ"). There are 12 animals sampled form modern endotherms
Yep, I bet this is 4 birds and 8 mammals - right?
But even a sample size of 12 is still disturbingly small. To get really
good statistics one wants sample sizes of at least 40-50, and hundreds
is even better.
Furthermore, unciritcally lumping mammals and birds in a single
regression line rather tends to beg the question. It is simply not
neccessarily the case that mammals and birds fall on the same
regression line. This means that a composite sample, especially such
a *small* composite, with so few birds in it, cannot be considered
very reliable. One should separately analyze the mammals and the birds
and then *test* for equivalence, not assume it.
> and 9 from modern ectotherms. The regression lines (on a log-log
> plot) for the nasal cross-sectional areas vs. mass are clearly
> distinct for the two groups. The study was not based merely on "a
> sample size of four". Perhaps Jonathan's defense makes a bit more
> sense now?
Very little, 12 is not really *that* much better than 4.
And most of the 12 are the wrong animals to use for dinosaur
analogs. If it had been 12 *birds*, including several non-ratites,
then the result would be *slightly* better, but still inadequate.
> Greg's "problems" with the undersampling of the variability in
> nasal cross-sectional areas of extant animals ought to explain why
> these areas fall on such nice regression lines if there's no
> significance here.
Well, we don't really know that the samples were random anyhow. If
there was any selectivity in choosing the organisms to include in the
study, even an unconsious selectivity, this sort of significance could
*easily* be a total artifact.
Secondly, even if *on* *average* an endotherm has larger RT's than
an ectotherm, this does not mean that large RT's are *required*
for endothermy, which is what is needed to use them to show that
dinosaurs were ectotherms. As long as even *one* living endotherm
lacks large RT's then it is still *possible* for dinosaurs to be
endotherms with small RT's. This is the *real* problem with under-
sampling. The correlation could well be entirely real and dinosaurs
could *still* be endotherms. Without a larger sample one simply cannot
evaluate the level of *overlap* between the two regimes, which can
occur even if the averages are widely separated.
The peace of God be with you.