Hi

On 28 Sep 2002, Donald Burrill wrote:
> "Omitted" might be unexceptionable -- that's part of the definition of a
> lurking variable, after all.  But "confounding" is already VERY well
> defined, and represents a different idea altogether.  (In particular, a
> confounding variable is already present and measured, unlike a lurking
> variable;  and it is in some considerable degree redundant with other
> present variables (those with which it is confounded), again unlike a
> lurking variable -- which, it is supposed, is not only not redundant but
> represents something unmeasured and by extension probably not even
> correlated with the variables presently in hand.)

My experience (in psychology) with confounding is different than
Donald's.   Confounding variables need not and often are not
measured.  Part of analyzing a study is identifying potential
unmeasured confounding variables.

Best wishes
Jim

============================================================================
James M. Clark                          (204) 786-9757
Department of Psychology                (204) 774-4134 Fax
University of Winnipeg                  4L05D
Winnipeg, Manitoba  R3B 2E9             [EMAIL PROTECTED]
CANADA                                  http://www.uwinnipeg.ca/~clark
============================================================================

.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to