[From Bruce Abbott (970417.1025 EST)]
Rick Marken (970417.1300 PDT) --
I asked Bruce Abbott:
What do you agree with, Bruce? Martin's notion of how to do science? Or
his remarkable analytic discovery that
> there is imperfect information about the disturbance passed by
> the perceptual function
Answer: I agree with _all_ of Martin's post.
Bruce Abbott (970416.1055 EST)
I'd be very much interested to hear Rick Marken's impression of Richard
Kennaway's paper, "the physical meaning of the correlation coefficient for
bivariate normal distributions." Rick?
I hope I'll have a version that I can read this weekend. But based on the
discussion I've seen so far I'd say that Richard's paper would be a rather
severe disturbance to the perceptions being controlled by someone who is
writing a statistics textbook for behavioral scientists.
Now why would you say that? Richard's analysis of the usefulness (or
uselessness, depending on size) of individual correlational relationships
for the purpose of predicting Y given X is right on the mark, and I said so.
Actually, I find it quite gratifying that his analysis confirms my own
understanding of the subject. When you are writing a textbook on a subject,
it's nice to have independent confirmation that you understand the subject
correctly.
The only point at which I take issue is that Richard's declaration that low
correlations (0.50 or below) are "useless" may be misunderstood. What he
means by that is that they are useless _individually_ for the _purpose of
predicting the Y-value of a point from its X-value_ (or vice versa). As I
have noted, this does not mean that they are without scientific merit for
other purposes, which may account for such correlations being frequently
reported in the scientific literature.
Undisturbed,
Bruce