NO MORE Psychologist

CSGnet Archive CSG1997
1

Bruce you have it BACKWARDS --- the statement should read "Psychology has
nothing to do with mind or behavior -- that is subject matter of the field of
PCT"

Psychology is the study of Coercion --- If it were a true science it would
have proven it's self wrong long ago. The only predictive validity psychology
has is when it applies to coercion. Anything out side of that Psychology is
more akin to Astrology and the reading of Tea leaves. Rarely if ever
psychology accounts for 50% of the Variances in any controlled Variable --
thus your prediction is just as good or better then psychology, if you flip a
quarter.

If I were to label myself as a scientist it surely would not be because of
what I learned from Psychology -- It WOULD BE BECAUSE OF WHAT PCT HAS TAUGHT
ME.

I have tried to be as dispassionate as I could -- hope you can tell what side
of the fence I am on :slight_smile:

Mark Lazare

2

[From Bruce Abbott (971218.1505 EST)]

Bruce you have it BACKWARDS --- the statement should read "Psychology has
nothing to do with mind or behavior -- that is subject matter of the field of
PCT"

Mark, if psychology is _defined_ as the study of behavior and mental
processes, then that is what it is. If you wish to assert that PCT is the
only _true_ psychology, that is another issue.

Psychology is the study of Coercion --- If it were a true science it would
have proven it's self wrong long ago. The only predictive validity psychology
has is when it applies to coercion. Anything out side of that Psychology is
more akin to Astrology and the reading of Tea leaves. Rarely if ever
psychology accounts for 50% of the Variances in any controlled Variable --
thus your prediction is just as good or better then psychology, if you flip a
quarter.

I don't know where you are getting these opinions from, but they don't seem
to be founded on any real knowledge of psychology. "Psychology is the study
of coercion?" Come on, Mark. Most of psychology has nothing whatsoever to
do with coercion. In fact, most of it is purely descriptive. What is
coersive about the study of learning? Memory? Sensation? Perception?
Emotion? Stable personality traits? Psychological disorders? Cognitive
development? (Just to name a few areas of study.) Your statement doesn't
stand up even to casual scrutiny.

As for your statistical statement, I'm sorry, but you don't really
understand what you are talking about. I let it pass the first time, but
since you persist in making this assertion, here's something for you to
think about. R-squared is not a probability, and the fact that 50% of the
variation in Y may be "accounted for" by variation in X has has nothing
whatsoever to do with the probability of getting "heads" on the flip of a
fair coin. If I guess "heads," I stand a 50-50 chance of guessing right.
If I discover that 50% of the variation in GPA can be accounted for by
variation in IQ then I can cut the average error in my prediction of GPA in
half by knowing the IQ. Cutting prediction error in half is not the same as
making a guess and having a probability of being right of .5.

By the way, earlier you mentioned that one of your dissertation committee
members asked for a significance test on your .997 correlation. Aside from
the lack of need for such a test even where it could be done, the request
ignores the fact that significance tests on correlations derived from your
study would be invalid because the sequential points collected cannot be
considered independent observations of the X-Y pairing.

If I were to label myself as a scientist it surely would not be because of
what I learned from Psychology -- It WOULD BE BECAUSE OF WHAT PCT HAS TAUGHT
ME.

Whether one is doing science depends on whether one is using the scientific
method, not whether one subscribes to a particular theory.

I have tried to be as dispassionate as I could -- hope you can tell what side
of the fence I am on :slight_smile:

Unfortunately, too much passion can get in the way of good reasoning.

Regards,

Bruce

3

[From Bruce Nevin (971218.1745)]

Bruce Abbott (971218.1505 EST) --

"Psychology is the study
of coercion?" Come on, Mark. Most of psychology has nothing whatsoever to
do with coercion. In fact, most of it is purely descriptive. What is
coersive about the study of learning? Memory? Sensation? Perception?
Emotion? Stable personality traits? Psychological disorders? Cognitive
development? (Just to name a few areas of study.) Your statement doesn't
stand up even to casual scrutiny.

If I understand him, Mark is saying that, if your basis of explanation is
linear causation, then the only way to get consistent results in the study
of living organisms is by compelling the response that is predicted, e.g.
by keeping an animal hungry in conditioning experiments and limiting the
available means for getting food. It's the only way that's been found for a
linear causative explanation to deal with the Guthrie's lens
paradox--variable and inconsistent means produce consistent ends.

Perhaps you have examples of research with results exceeding .95
correlation whose explanations are couched in linear causation but whose
methods do not involve deprivation, constraint, and other forms of coercion.

If I guess "heads," I stand a 50-50 chance of guessing right.
If I discover that 50% of the variation in GPA can be accounted for by
variation in IQ then I can cut the average error in my prediction of GPA in
half by knowing the IQ. Cutting prediction error in half is not the same as
making a guess and having a probability of being right of .5.

The 50% correlation is perfectly fine as long as it refers the particular
population for which the correlation was found. The problem begins when you
apply it to other populations, and becomes acute when you apply it to
populations of one, to individuals, whether they are in the original
population or not. Then you might as well flip a coin -- once for each
individual. And such population measures are routinely applied to
individuals, aren't they? In my experience, they are routinely presented as
significant generalizations about "people", where the term "people" (or the
like) is ambiguous between population and individual, ambiguous to the
point of prevarication IMO.

Your objection to Mark's coin flip comparison trips over this ambiguity, I
think. The .5 correlation is over a population. The coin flip is one
individual at a time. "Sam's GPA will correlate with his IQ, yes or no."
(Flip) "Gail's GPA will correlate with her IQ, yes or no." (Flip). Half the
time you're right. Tough luck on the smart kid frozen out of a scholarship
because the application of statistical measures to individuals tipped the
balance on the record. But helpful to admissions officials and aid
officials who need a winnowing sieve, and wouldn't be caught dead flipping
a coin.

I'm not a psychologist, so maybe I just don't understand these deep
matters. Help me out. (I may even be able to answer sometime.)

  Bruce Nevin

4

[From Richard Kennaway (971219.15:00)]

Bruce Abbott (971218.1505 EST)

If I discover that 50% of the variation in GPA can be accounted for by
variation in IQ then I can cut the average error in my prediction of GPA in
half by knowing the IQ.

Don't you mean "average squared error"?

Anyway, here are some figures from my recent paper "Population statistics
cannot be used for reliable prediction". (Not online; paper copies
available on request.) These are for the bivariate normal distribution. I
expect the figures to be broadly similar (i.e. bearing out the title of the
paper) for other distributions.

If R-squared is 0.5, then the correlation c is 0.707 (i.e. sqrt(0.5)).

From this it follows that knowing one variable reduces the standard

deviation in measurements of the other by a factor of 1.414. This is
equivalent to exactly 0.5 bits of information. To put it another way, it
reduces the average absolute error by about 30%.

In practical terms, the probability of correctly guessing whether GPA is
above average, given the exact value of IQ, is 0.75. The proportion of the
population whose IQ is so far away from average that the prediction
regarding GPA is 95% likely to be correct is about 10%. At the 99%
confidence level, the proportion is 2% -- i.e. the membership of Intertel
(who accept the top 1% on IQ tests), plus a few simple folk from the other
end of the distribution. The probability of guessing the GPA to within
half a decile is just under 20% (compared with 10% by chance). Almost none
of these predictions are likely to be correct with 95% confidence. A
non-random subpopulation of 50% of the whole could display a correlation
less than 0.3.

Just a few figures to give concrete meaning to the phrase "explaining half
the variation".

-- Richard Kennaway, jrk@sys.uea.ac.uk, http://www.sys.uea.ac.uk/~jrk/
   School of Information Systems, Univ. of East Anglia, Norwich, U.K.

5

08:00 PST 971219 David Wolsk defended his honour:

Bruce you have it BACKWARDS --- the statement should read "Psychology has
nothing to do with mind or behavior -- that is subject matter of the field of
PCT"

snipped

Psychology is the study of Coercion --- If it were a true science it would
have proven it's self wrong long ago.

I learned some useful ideas from Bowlby's studies of infant development and
Harry Harlow's monkey work with surrogate mothers and Kurt Lewin's social
psych approach, etc. Correlational studies are really a small part of the
field. My doctorate was in psychophysics ..... 4 subjects analysed
individually.

In criticising the field, which I do all the time, much of where I come from
is based on the general pattern of academia ...... the continual development
of ever narrower fields of specialization, each with its own journals and
languages and career patterns. Its as damaging in medicine, law,
engineering as it is in the social sciences. Geography seems like the last
holdout for breadth.

Two encouraging trends:
1. The spread of the Metropolitan Universities group, mostly USA, oriented
to adult learners studying part-time. Their orientation is more real-life,
problem stuff.
2. The university co-op programmes ......students in real-life job situations.

I'm not sure what any of this may mean for PCT. I sense a growing
awareness, as the world gets to be a more dangerous place and the proposed
solutions are obviously driven by global corporate agendas. that we need to
be questioning academia on a more useful basis. Perhaps its up to us to use
the summer Vancouver meeting as an opportunity for some creative marketing
...... street theatre .....no, Theatre of the Oppressed ...... a chicken
and a hen pecking out their cage-size preferences together ......a PCT
analysis of George Soros .....or Quebec's P.M. Lucien Bouchard. The future
of Canada may be in our hands ......or PC systems. After all this is the
land of the PCers .....the Progressive Conservative Party, and they are
enormously interested in CONTROL.

Happy holidays
David W.
Victoria, BC Canada

ยทยทยท

At 12:33 18/12/97 EST, Mark Lazare wrote:

6

[From Bruce Abbott (971219.1155 EST]

Richard Kennaway (971219.15:00) --

Bruce Abbott (971218.1505 EST)

If I discover that 50% of the variation in GPA can be accounted for by
variation in IQ then I can cut the average error in my prediction of GPA in
half by knowing the IQ.

Don't you mean "average squared error"?

Yes. R-squared represents the proportion of variance accounted for;
variance is the average squared error.

Bruce Nevin (971218.1745) --

The 50% correlation is perfectly fine as long as it refers the particular
population for which the correlation was found. The problem begins when you
apply it to other populations, and becomes acute when you apply it to
populations of one, to individuals, whether they are in the original
population or not. Then you might as well flip a coin -- once for each
individual. And such population measures are routinely applied to
individuals, aren't they? In my experience, they are routinely presented as
significant generalizations about "people", where the term "people" (or the
like) is ambiguous between population and individual, ambiguous to the
point of prevarication IMO.

If the person in question is a member of the population for which the
correlation applies (e.g., a high-school student applying for admission to
college), then for the person who has to make a decision about this
individual (e.g., admit to college or not) the information may be _much_
better than a flip of the coin, in the sense that it leads to the correct
decision being made more often than would be the case absent this
information. Thus, if students who have a high-school GPA above a certain
value are much more likely to succeed in college than those whose
high-school GPA below that value, and this is all the information one has
about the person, and there is a limited number of classroom seats available
(i.e., some must be turned down), then the decision-maker can improve the
rate of student success in college by applying this criterion and admitting
only those whose high-school GPA falls above it.

Such a strategy will still admit those who, for various reasons, will not
succeed in college and it will deny admission so some who, for various
reasons, would have succeeded, but that is the price to pay for having only
limited information about the individual. The decision-maker still must
"flip a coin," but by gathering data on student variables that correlate
with degree of success in college, he or she can bias the coin heavily in
favor of making the right decision. By combining information from a number
of sources (e.g., high school GPA, SAT score, letters of recommendation,
etc.), one can usually do better than one could by relying on a single
source (Multiple R higher than any single r).

I'm not a psychologist, so maybe I just don't understand these deep
matters. Help me out. (I may even be able to answer sometime.)

Bruce, what _is_ your field? Linguistics? Judging from the quality of
thought expressed in your writing, I very much doubt that you have any
trouble understanding these "deep matters," psychologist or not.

Regards,

Bruce