I'm analysing about 20 lab-results of three different groups either with ANOVA, Kruskal–Wallis test or chi-squared. I correct the resulting p-values for multiple testing using the Benjamini/Hochberg procedure. I create post-hoc tests for significant variables using Tukey, Dunn and chi-squared.

My questions are: do I have to correct the post-hoc tests for multiple testing (which is the default in most statistics software) and if so, how do I adjust in qualitative variables/chi-squared?

A statistician once told my colleague it was not appropriate to adjust p-values in post-hoc tests.

  • $\begingroup$ This is probably a duplicate, but I cannot find it ... so search this site! $\endgroup$ – kjetil b halvorsen Jun 29 '18 at 9:42
  • $\begingroup$ The term to search for is: "Multiplicity adjusted P values" $\endgroup$ – Harvey Motulsky Jun 29 '18 at 20:27

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.