Re: main effect of covariate in Repeated Measures Design

Posted by Swank, Paul R on Aug 19, 2013; 7:04pm
URL: http://spssx-discussion.165.s1.nabble.com/main-effect-of-covariate-in-Repeated-Measures-Design-tp5721647p5721654.html

In the presence of an interaction, the main effect should not be interpreted alone but only in the context of the interaction.

Paul R. Swank, Ph.D., Professor
Health Promotions and Behavioral Sciences
School of Public Health
University of Texas Health Science Center Houston
________________________________________
From: SPSSX(r) Discussion [[hidden email]] On Behalf Of Sesch [[hidden email]]
Sent: Monday, August 19, 2013 9:36 AM
To: [hidden email]
Subject: main effect of covariate in Repeated Measures Design

Hello there,

I've spent a considerable amount of time trying to google this particular
problem, but I can't seem to find that specific answer I'm looking for. So I
thought I'd just ask here.

So I'm working with a repeated measures design that also includes a
continuous moderator. The moderator is entered as a covariate. After I found
out how to probe the interactions between within factor and covariate, I
still have problems with interpreting the main effect of that covariate. If
you get a significant main effect you'd usually write a word or two about
the direction of that main effect, but I don't seem to be able to identify
the direction from the "Between Subjects" output.

So what do I do? Should I look at the interactions and try to indentify the
main effect through that? Is that the right way to do this?

I'll be more than grateful for any helpful comment!



--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/main-effect-of-covariate-in-Repeated-Measures-Design-tp5721647.html
Sent 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