Cognitive dissonance, Methods

[R_Marken]

[From Rick Marken (971204.08250)]

Bruce Abbott (971204.0925 EST)

The kinds of conflict situations that were studied under cognitive
dissonance theory would seem to be excellent candidates for
individual research conducted in the light of PCT, don't you think?

Yes.

Bruce Abbott (971204.0945 EST)--

A repeated measures design is an individual subject design replicated
as many times as there are subjects. Nothing precludes the
investigator from examining the data for each individual separately,
and large differences in the trends of individual subjects would
show up as a large error term within the ANOVA, as well as big
standard errors around at least some of the individual means.

Everything you say here is wrong. Only the average results of
repeated measures designs are reported as "the results" so any
differences between subjects, even if noted, contribute nothing
to revision of the "theory" being tested by the group data. The
conclusion will be reported as "A effects B" even if this is only
true of a majority (or even a minority) of the subjects tested.
Regarding individual trends, I consider it a "large difference
in trend" if the effect of A on B is positive linear for one
individual, negative linear for another, U shaped for another
and inverted U for still another. This is how the individuals
responded in my "oh god, not again" spreadsheet. My eyeball
estimate (based on the fact that the within groups variance was
about 1/100th of the between groups variance) is that the F
would be significant at the .001 level, minmimum. Since there
were only 10 subjects I suspect that the IV picked up well over
70% of the variance in the DV, so the effect of A on B would be
considered a "strong" effect.

It's clear that neither you nor Martin are going to change your
minds about the merits of conventional research methods. So
just go ahead and do research in whatever way you want (Martin
is really no threat since he doesn't do research). If you end up
doing PCT research using conventional methods (as have Carver
and Scheier and their ilk) then your research will just be
ignored (as is that of Carver and Scheier) by those of us who
are interested in understanding purposeful behavior. But you
might get some attention from the psychological establishment,
allowing them to continue to believe (with you) that PCT is
something other than what it is.

Best

Rick

···

--
Richard S. Marken Phone or Fax: 310 474-0313
Life Learning Associates e-mail: rmarken@earthlink.net
http://home.earthlink.net/~rmarken

[Martin_Taylor4]

[Martin Taylor 971204 21:25]

Rick Marken (971204.08250) to Bruce Abbott (971204.0925 EST)

It's clear that neither you nor Martin are going to change your
minds about the merits of conventional research methods.

Speaking for myself, I'm curious as to why you would want me to, since
you don't seem able to determine what I think about "conventional
research." What I'm curious about is to get an idea what your imagined
"martin-in-the-mind" thinks about the merits of conventional research,
because I suspect it would be rather fun to compare it with what
I, the live Martin, think about it.

And then it would be interesting to find out what is wrong with both the
imagined opinion and the real opinion. I realize the opinion of your
"martin-in-the-mind" won't change. It never does. But the opinion of
the living Martin changes about a lot of things, given reasonable
evidence that it is appropriate to do so.

Could it be that it presents a problem for you to find out that your
spreadsheet _really_ doesn't address the problem you said it did?
And is that why your response is (the predicted) ad hominem, rather
than presenting the significance test that was requested? After all,
if you want to criticize "conventional research," you should do it
by using their methods properly, shouldn't you?

(When I say "the predicted" I am referring to a posting I wrote some
days ago but never sent, which was a satirical one pointing out the
demonstrations of the validity of S-R theory that occur daily on CSGnet.
Stimulus: a message that suggests some variation, extension, or analysis
of canonical PCT, or, horrors, the possibility that PCT might offer a simple
explanation of some everyday or experimental observation; Response: a
posting by Marken asserting that the poster believes in "conventional
research," "information theory and trendy science," "reinforcement
theory" or some such bugaboo, and is devoting his (or, occasionally her)
efforts on CSGnet to the destruction of PCT.)

So
just go ahead and do research in whatever way you want (Martin
is really no threat since he doesn't do research).

So, anyone who does research is a threat? And working through theoretical
constructs is not research? That is indeed an insight into the ways
of Science over there in La-la Land:-)

Martin