What I have done with such designs is to run a one way ANOVA on the five
groups but include 4 contrasts:
contrast HA AS AM
NS NM
Impaired vs not 4 -1 -1 -1
-1
Amn vs Non amn 0 -1 -1 1
1
Single vs Mult. 0 1 -1 1
-1
interaction of
AMN by domain 0 -1 1 1
-1
These are orthogonal. Additional paired comparsions (say of each
ompaired group with Normals) can be done with appropriate correction for
type 1 error.
Paul R. Swank, Ph.D. Professor
Director of Reseach
Children's Learning Institute
University of Texas Health Science Center-Houston
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of
KEVIN MANNING
Sent: Thursday, April 19, 2007 3:59 PM
To:
[hidden email]
Subject: Question about nesting group membership in ANOVA
Dear list-mates,
I would greatly appreciate help with this problem. I have 5
groups: healthy adults, and 4 groups of cognitively impaired
participants. The impaired participants are amnestic and non-amnestic.
Within these two groups, they are impaired in either a single domain of
cognition or a mutiple domain. So I have something like this:
Groups:
Normals Amnestics
Non-Amnestics
(Single, Mutiple Impairments)
(Single, Multiple Impairments)
I would like to run an analysis of variance of a cognitive test and
compare normals, amnestics, and non-amnestics, in addition to
determining the effects of being either impaired in a single or mutiple
domain of cognition.
Can someone help me with this? Thanks!
Kevin Manning
Locked
