Posted by
Garry Gelade on
Jan 10, 2012; 2:59pm
URL: http://spssx-discussion.165.s1.nabble.com/GLM-repeated-measures-concern-question-tp5104022p5134272.html
Dave
I think your CONTRASTS Polynomial(1 8 32) is correct. CONTRASTS Poylnomial without the set sizes will assume equal spacing of your IV (e.g. set sizes of 1,2,3 or 1, 11, 21).
One way to check would be to request SPSS to print the contrast coefficients (Lmatrix). For testing the linear trend, the spacing of (difference between) successive contrast coefficients should be in the same ratio as the spacing of your set sizes, i.e. 7:24.
Regards
Garry Gelade
Business Analytic Ltd
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of eyeman03
Sent: 09 January 2012 14:14
To:
[hidden email]
Subject: Re: GLM repeated measures concern/question
First, thank you* EVERYONE* for your input. It’s really appreciated.
Diana,
Let me expand a little on the design. We are studying the effects of two
types of simulated central blind spots on adaptation. The task is Visual
Search with 3 set sizes (1, 8, 32)
The research design is a mixed 2x2 ANOVA with adaptation as the within
effect, and blind spot type as the between effect. The statistical tool is
GLM Repeated measures.
As you know, our problem is the unequal spacing of the set sizes, and
whether or not SPSS intrinsically recognizes the spacing as equal. You
answered that question; yes, it does.
We’ve come to learn we can use the CONTRAST option for set size. However,
If we add set size as a covariate (as you suggested), then SPSS will not
recognize it as a factor (CONTRAST).
But if set size is added as a Between-Subject factor , we can now write
syntax as a CONTRAST: /CONTRAST(Set size)=Polynomial (1, 8, 32).
We ran two different syntaxes to compare their CONTRAST results. :
*/CONTRAST(Set size)=Polynomial (1, 8, 32)* vs /CONTRAST(Set
size)=Polynomial.
With the *former syntax*, only the linear contrast was significant. With
the latter syntax, both the linear and quadratic contrast were highly
significant.
So the output analysis with stating vs not stating the set sizes made a
significant difference.
We wanted to ask you opinion if this syntax solution: CONTRAST POLYOMIALS
(1, 8, 32) seems correct for our analysis
Dave
PS……I can send the Output data if anyone is interested.
--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/GLM-repeated-measures-concern-question-tp5104022p5131418.htmlSent from the SPSSX Discussion mailing list archive at Nabble.com.
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD