I have 13 subjects all who completed 3 different warm-up protocols. I want to compare the results of their countermovement jump height test results after each warm-up. My data is not normally distributed. Is there a difference between conducting a Friedman test and post hoc test to see where the difference lies or conducting threeWilcoxon Signed Rank tests between each warm-up to see where the differences lie ?

  • 2
    $\begingroup$ Yes there is a difference. Friedman test is not the direct extension of the Wilcoxon test (in a manner like ANOVA is the extension of t-test or Kruskal -Wallis is the extension of Mann-Whitney). Friedman test has its own post-hoc pairwise comparison procedure invented. $\endgroup$
    – ttnphns
    Commented May 12, 2015 at 13:55
  • $\begingroup$ I think the sign test is the paired test that corresponds to the Friedman. $\endgroup$
    – Glen_b
    Commented May 12, 2015 at 23:29


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.