Date:         Mon, 13 Mar 2000 10:35:44 -0500
Reply-To:     "Andrew F. Hayes" <Andrew.F.Hayes@DARTMOUTH.EDU>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         "Andrew F. Hayes" <Andrew.F.Hayes@DARTMOUTH.EDU>
Subject:      Re: Negative Coefficients
In-Reply-To:  <Pine.A41.4.21L1.0003131026020.94306-100000@login0.isis.unc .edu>
Content-Type: text/plain; charset="us-ascii"

>The result that you describe is often described in the literature as
>"suppression."  It is not all that unusual in non-experimental
>analyses... The magnitude/pattern of intercorrelation among the
>independent variables is the culprit...
>
>For a more complete explanation, see Cohen and Cohen (Applied Regression
>Analysis) or Darlington (Linear Models).
>

....as well as Smith et al. (1992). Suppressor variables in
multiple-regression correlation. Educational and Psychological Measurement,
52, 17-29.
======================================================
Andrew F. Hayes, Ph.D.
Research Statistician
Tuck School of Business at Dartmouth

Adjunct Assistant Professor
Department of Psychological and Brain Sciences

DARTMOUTH COLLEGE
HANOVER, NH 03755
603-646-3741

Research Computing on the WWW:
http://mba.tuck.dartmouth.edu/pages/admin/research/
To make a Research Computing Request:
http://mba.tuck.dartmouth.edu/pages/admin/research/rrequest.htm
Personal Web Page:
http://mba.tuck.dartmouth.edu/pages/faculty/Andrew.Hayes
=========================================================