Repeated measures with a continuous between-subject variable
hi all,
I'm trying to build a repeated measures model (called levels in the next description) where I have two-between subjects variables, one being nominal (gender, two levels) and one being a continuous variable (a score at a particular questionnaire).
I tried with ANOVA, but the continuous measure can only be used as covariate. As a result, I cannot get the 3-way interaction that I'm interested in (gender * questionnaire score * levels).
Is there a way to build such a model? what would be, eventually, the way to set it up?
thanks in adance
Comments
This type of model can be built as a liner mixed model - rmANOVA does not support it.
thanks for your suggestion.
One thing is not clear, and I couldn't find examples online on how to set up this analysis.
Compared to the repeated measure ANOVA table, to do a linear mixed model I rearranged the table in long format. I set up the analysis as showed in the attached image, but I'm having issues with df. Since I have 133 subjects, the df for sex, questionnaire, and rm (repeated measure, 3 levels) shouldn't be 387. Is there a way to specify which one of these variables is the repeated measure one?
thanks
AFAIK JASP doesn't support adding random slopes (to indicate that the effects are RM).
If you work in R, you can do this with the lmerTest package.
I am pretty sure we offer a complete analysis, but I'll forward this to the experts.
Cheers,
E.J.
Hi Nicola,
sorry for the late reply. Yes, JASP allows fitting repeated measures models within the mixed model interface. The analysis tries to automatically fit the maximum random effects structure that's justified by the data. However, the warnings below the output table indicate that your repeated measure factors were removed from random effects. Unfortunately, I can't tell more from the output that I see. Could you please sent me the data, so I check that they are correctly formated? (f.bartos96@gmail.com)
Cheers,
Frantisek