Hello everyone,
I have used a multivariate repeated measures ANCOVA (GLM repeated measures) in order to analyse the following:
the effect of the moderator (continuous, measured at baseline) on the effect of an intervention (2 groups with different intervention strategies: condition 1 and 2) on the DVs (2 DVs, both consisting of a pre-intervention and post-intervention measurement).
In this output, I get a significant Sig. for Wilks' Lambda in the Multivariate Tests table for the between subjects effect of my covariate and for the within subjects effect of ''time''. Furthermore, I have significant Sig. for DV1 (in the row of my covariate) in the Tests of Between-Subjects Effects, for DV2 this is not the case.
I am having some trouble interpreting this output. I figured it meant the treatment had a significant effect (because ''time'' is significant)? Also is it safe to say there is no moderation effect (because there was no significance for time*condition or time*covariant)
Or should I have conducted a different analysis?
Thanks a lot to anyone willing to help!
kind regards
Hello Floor,
1. Significant covariate effect indicates that scores on covariate/moderator and DV1 were related/associated. (but not so for DV2, since it appears you're looking at univariate results)
2. Significant time effect indicates that for some combination of DV1 and DV2, there was a non-zero change between pre- and post- scores on the DV(s).
It could be the case that both treatments influenced the differences nearly equally; or it could be the case that something unrelated to the treatments influenced the pre-post differences (perhaps just the act of measuring at pre-treatment itself, the so-called "pretest effect"). However, as neither the main effect of treatment or (more important) the treatment x occasion interaction was significant, you can't presume differential effectiveness between treatments.
If your chief aim was to evaluate moderation effects, then a somewhat different model might be more informative. Specifically, you'd like to include moderator X treatment interaction term(s) in the model. You can do this with manova, or with multivariate regression.
Good luck with your work.
Hi,
Did you include the moderator variable in the analysis?
You can calculate the standardized variable of time*var
Hi,
Thank you both for your answers!!
I have now also found, for DV1, a significant threeway interaction of the condition*time*covariate (so, betweensubjectsfactor*withinsubjectsfactor*moderator).
Now I want to find the way in which the covariate moderates the interaction (time*condition). The output of the repeated measures ancova does not provide neither tables or graphs that give me this information.
I got the suggestion of using Hayes' Process macro to investigate the moderation effect, however to my knowledge i cannot compute this analysis with a within-subjects factor. We could compute the difference scores of our DV ourselves (so getting rid of within-subjectsfactor) but we got the recommendation not to use difference score, since it could influence the range.
Does anyone have advice so we can investigate the moderation effect more in dept?
Kind regards
- Badges
- Science topic