1
$\begingroup$

I have an intervention in a group of schools. I think I need to use RM anova since RM Anova is 1 factor between subjects and other one within subjects (time) while factorial anova is two factors between subjects -is it correct? I have 4 subscales and I have pre and post scores. I want to see if the intervention was effective or not. Also one other question my control group is much smaller than my intervention group due to availability. Thanks for your advice.

$\endgroup$
2
$\begingroup$

You certainly need to account for the dependence of the data, so regular ANOVA is not an option. However, RM-ANOVA makes assumptions that are rarely met in repeated measures - in particular, it assumes sphericity.

It would probably be better to use a multilevel model. These make fewer assumptions.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.