I have a significant interaction between within and between factors. Planned contrasts for simple effects revealed significant difference in one group, but no difference in the other group (as expected). Do I need to employ alpha correction for the simple effects in this case?


  • $\begingroup$ I can't think of any multiple comparison problems when you wouldn't want to use alpha correction. Maybe this question would be helpful. $\endgroup$
    – Anson Call
    Sep 2 '17 at 17:59
  • $\begingroup$ Thank you for reply. I read different approaches to this problems, some argue that we must correct for all multiple comparisons, and some argue that in small number of planned comparisons that derive from the interaction, alpha correction is not required. $\endgroup$
    – Ruth Nash
    Sep 2 '17 at 18:42
  • $\begingroup$ Also, If I hypothesized that one comparison will yield non-significant results, do I need to include it in the number of multiple comparisons? $\endgroup$
    – Ruth Nash
    Sep 2 '17 at 18:46

Your Answer

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

Browse other questions tagged or ask your own question.