Werner Wittmann wrote:
>
> See the regression artifact primer at Dave's homepage:
> http://nw3.nai.net/~dakenny/rrtm.htm
I looked at
http://nw3.nai.net/~dakenny/primer.htm
and found myself puzzled by the Galton squeeze plot (or is it a pair
link diagram, or are they one and the same?).
It shows the initially extreme subjects converging toward the mean,
but if this were purely regression to the mean, the cross-sectional
post-test SD would be equal to the pretest SD. In the diagram, the
post-test SD is clearly smaller. However, I have not read the book
or the Galton article from which the diagram was extracted, both of
which may contain additional material to clear up my confusion.
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
