3
$\begingroup$

After performing an ANOVA and then doing post hoc tests with a Tukey HSD test is it still necessary to correct for multiple pairwise comparisons or is that done already?

$\endgroup$
9
$\begingroup$

It is not necessary to correct for multiple comparisons when using Tukey's HSD. The procedure was developed specifically to account for multiple comparison and maintains experiment-wise alpha at the specified level (conventionally .05). Page 210 of Maxwell and Delaney's book on experimental design has explanations and examples of the procedure.

$\endgroup$

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.