05-24-2018 02:21 PM
I am trying to find a way to calculate the power and sample size necessary for a 2x2x2x4 mixed factorial design as well as calculate the power necessary for a moderator analysis.
I have one between factor with two levels and three within factors (2 levels, 2 levels, 4 levels respectively).
The above resource has been the best one I have found, but I am feeling a big lost. The PASS program doesn't appear to have the ability to handle more than two within factors for a repeated measures mixed model and Gpower doesn't have a mixed model component that allows a user to indicate more than one within factor.
Is there a resource or guidance anyone can provide on the best way to calculate the necessary sample size? Most of the resources I've in programs such as R are limited to the number of within factors you can have in the simulation.
05-26-2018 04:53 PM
For a model of this complexity, basically your options are simulation or a clever use of PARMS / HOLD that Walt Stroup has written about:
Ch 16 in
Even with this tool, you may still be a bit lost because of the challenge of specifying one (or many) alternative hypotheses in a four-way factorial treatment design. I would be, anyway.