| Date: | Wed, 17 Apr 2002 17:13:26 -0400 |
|---|
| Reply-To: | "Burleson,Joseph A." <burleson@up.uchc.edu> |
|---|
| Sender: | "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU> |
|---|
| From: | "Burleson,Joseph A." <burleson@up.uchc.edu> |
|---|
| Subject: | Re: test for trend in repeated measures |
|---|
|
| Content-Type: | text/plain; charset="iso-8859-1" |
|---|
Karen: GLM supports the POLYNOMIAL option for repeated measures. The first
polynomial is the linear trend (positive means rising; negative =
declining); 2nd polynomial is quadratic, etc. for 1 fewer trends than you
have points available. One can chose equal spacing between time points, or
specify the spacing.
-Joe Burleson
-----Original Message-----
From: Scheltema, Karen [mailto:KScheltema@HEALTHEAST.org]
Sent: Wednesday, April 17, 2002 5:02 PM
To: SPSSX-L@LISTSERV.UGA.EDU
Subject: test for trend in repeated measures
I nosed around through the menus, including GLM, and could not find a way to
test for a linear trend in repeated measures. I have six contiguous
measures of bone density for 29 people that I want to look for a linear
trend in. I don't have the time series module. Thanks.
Karen Scheltema, M.A., M.S.
Statistician
HealthEast
Research and Education
1700 University Ave W
St. Paul, MN 55104
(651) 232-5212 (phone)
(651) 641-0683 (fax)
kscheltema@healtheast.org
|
