On Tue, 26 Dec 2000 16:32:54 -0600, jim clark <[EMAIL PROTECTED]>
wrote:
>There is a considerable literature on clinical judgment (i.e.,
>interview and human judgement) vs. actuarial predictions (i.e.,
>predictions from demonstrably valid regression equations ...
>human judgment _might_ be used in producing individual predictor
>scores, but not in aggregating them). In general, human judgment
>does not fare all that well relative to actuarial (i.e.,
>statistical) methods. Interesting that someone posting to a
>statistical newsgroup would advocate the non-statistical approach
>to selection problems.
This is one possible view, depending on your psychological education,
background and experience.
Coming from a methodological background, you could, without problems,
offer lots of regression equations which were errorously claimed as
'demostrably valid' one or other day, scientific publication or
period.
Coming from test psychology, you would hesitate because reliability
and validity coefficents, usually, suffer from 'regression to the
middle', are too low for individual prognosis, explanantion (in the
meaning of Hempel/ Oppenheim) and don't take into account non-linear
relations or patterns which are quite common in psychology, social
psychology or medical psychology.
Coming from cognitive/ cognition psychology, you might admit that
subjects estimate relations as deterministic (p=1) as soon as
probability for a certain event is close to p=0.70, however, you would
also take into account that similtaneous analysis of the right
hemisphere (5% left) might be superior on judgements concerning a
special subject (under special conditions) when compared to the rather
'one-track-minded', correlated or global results of so-called
'psychometric tests'.
Coming from attributional psychology, you could cite findings on
attractivity of a subject (attractive subj are preferred), that, on a
subjective evaluation, an individual might be rejected/ refused
because of his/ her nose, however (and a little more professional and
experienced), you rather look for fingernails, shoes, type of
communication, cleanness, politeness, or in case of women, also for
the type of make-up (you don't take s/o who's sitting for 2 hours in
front of a mirror) *and* for his/ her abilties.
Also, there are lots of other views and experiences which are equaly
fundamented but do not exactly fit into the image of 'demonstrably
valid regression equations'. But I admit that there are also positive
findings which are valid for rats, doves, cats, dogs, humans -- but
not for gold fishes (contrast effect of the amount of reinforcement,
'Kontrasteffekt der Belohnungsmenge').
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
