2
$\begingroup$

I have a 4 (Time) x 3 (Size) x 3 (Type) Repeated Measures ANOVA. Since SPSS does not allow post-hoc analysis for repeated measures, I had to run individual t-tests one by one.

Assuming that I am only strictly interested in looking at the time domain, do I also have to account for the other comparisons in the size and type domain for bonferroni comparisons? Or do I just need to assume the total number of comparisons to those just within time?

$\endgroup$
1
$\begingroup$

You define everything before you do it, so if you are interested in the four comparisons for time, look at those four, adjust for making four comparisons, and do not look at the others.

If you start to deviate from your plan to examine those four, then you adjust for making 7 or 10 comparisons.

If you look at the original four, get an interesting result on the first comparison you do, and don’t bother with the other three, since you planned to do four comparisons, you still adjust for four comparisons.

Finally, Bonferroni is fine as a quick and dirty check, but it is completely dominated by Bonferroni-Holm in the sense that Bonferroni-Holm never does a worse job of controlling the type I error rate but at least sometimes has better power. At least consider using a more powerful method than Bonferroni.

$\endgroup$

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.