Hello all,

I am planning to perform a MANOVA using one independent variable which will contain 3 groups. Further I will include 5 dependent variables.

Now I was wondering if my MANOVA gives a significant difference what is the best correction to use in post-hoc testing ? I am afraid that by applying a Bonferroni correction the chance that a Type-II error will occur might be very real.

So my question is what might be the best alternative for this situation ? I was thinking the Tukey-HSD or Fisher's LSD test might be good alternatives. Or are there others that might be a better alternative ?