Hi Donald, thanks for the reply, but I'm afraid that didn't solve the problem for me. I re-ran the 2x2x2 full factorial analysis (not flexible factorial, but nevertheless) with equal/unequal variance, and assuming/not assuming independence with 3 different subject orders.
Changing the independence and variance parameters resulted in some changes in the results, as would be expected, but regardless of the combination of those parameters used, the results using the 3 subject orders always differed from one another. I'm at a bit of a loss to explain this now.
Thanks,
Ciara
|