On Wed, 19 Feb 2003, Mountain Bikn' Guy wrote in [art:
> Does anyone have an opinion on the following book?
>
> Multiple Regression: Testing and Interpreting Interactions
> by Leona S. Aiken, Stephen G. West, Raymond R. Reno (Contributor)
> Publisher: Sage Publications; ; (September 1996)
> ISBN: 0761907122
I have not read this book. There was an earlier book by Aiken & West
with much the same title, published I think about 1991, and I wouldn't
be surprised if this was a revised edition of that, with some
contribution(s) or other from Reno. My copy of the earlier book is
still in a box somewhere (I think!) since my recent move. I remember
disagreeing with some of their recommendations, at least partly because
they did not seem to be thinking in geometric terms; and I thought
their numerical simulation, presented at or near the end of the book,
was flawed in that (a) there was only one simulation, not a multiplicity
of simulated data for the same model and (b) the quadratic component
that was part of the model being simulated was detected, but (as I now
only vaguely recall) with a coefficient something like one or two orders
of magnitude smaller than the theoretical model called for.
But, as I said, I haven't read the 1996 book, so I don't know
whether the aspects that disturbed me have been addressed since 1991.
-- DFB.
-----------------------------------------------------------------------
Donald F. Burrill [EMAIL PROTECTED]
56 Sebbins Pond Drive, Bedford, NH 03110 (603) 626-0816
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
. http://jse.stat.ncsu.edu/ .
=================================================================
