You're welcome; IV-DV

From Ken Hacker [930406]

Bill, no disagreement on your response to my study. I believe that there
is much activity and essential stuff going on in error variance. As for
what to do with those not in the middle, I think that yes, they may be
more adaptable to what the majority is not. BUT, and this is a big one,
when the prevailing winds say ONE thing, and my findings may indicate TWO
things, that is no small finding. Ken

[From Bill Powers (930406.1330 MDT)]

Chuck Tucker (930405-2) --

The argument between the PCT modellers and the IT folks was
about the question: Can anything "outside" the living system be
found "inside" it? Answer: No.

Thank you very much.

You're very welcome. And what you and Clark are doing is watching
a lot of people milling around, right? It's all so simple when
you reduce it to its essentials.

ยทยทยท

-------------------------------------------------------------
Ken Hacker (930405) --

On the IV and DV comments made by Rick, Bill, Gary, and others,
I simply want to say that I believe that I CAN test for
signficant differences in linear relationships between
variables such as learning program A and learning program B
without and not intending to explain how subjects are
controlling the programs, their ouput, perceptions, or anything
else.

I've never meant to imply that you couldn't. The issue here, if
there is one, isn't about explaining individual characteristics
by mass measures. I'm simply raising the question of what you
will do about the people who respond to the two learning programs
oppositely to the way the group means go. You may find that
method B leads to better learning than method A, in terms of
group means. Would you then recommend switching from method A to
method B, even though the data show (as I predict they will) that
some people will do worse with method B? Or would you ignore the
group means, and let the people learn using whichever method
suits them best as individuals?

You're dropping hints that the choice will be between using
method A for everyone, or method B:

I am completely open to ways to test which kind of program is
more workable ...

The implication is "... more workable when used with everyone" as
opposed to " ... more workable for some of the people."
-------------------------------------------------------------
Out of deference to signs of impatience on the net, I've replied
to (some of) Martin Taylor's post directly.
--------------------------------------------------------------
Best,

Bill P.