>
>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.
>
>Best wishes
>Jim
>
This is a very good point, Jim. I'm curious if you, or others have noted the following irony. Psychology faculty know that the literature on the clinical judgement indicates it is very poor, yet in Search and Screen, Graduate Student admissions Graduate Student evaluations, most largely ignore this. When I'm on such committees I do a rank ordering based on whatever actuarial data is available and know that doing otherwise is just mucking around with error. Most other faculty haruspicate via predictors such as the "number of full professors who wrote letters of reference", "impression of the quality of their undergraduate school" or other voodoo. They are usually indignant when I point out that such variables add nothing above and beyond the actuarial data. Is there a difference between a psychologist and a psychic, I often wonder.
JR
/\
*||*
ox*=||=*xo
||
Jeff Rasmussen, PhD
"Welcome Home to Symynet"
Symynet http://www.symynet.com
Graphic Design
Website Development
Eastern Philosophies Software
Quantitative Instructional Software
||||
||||
================================================================= Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =================================================================
