As my data was extremely skewed, I have ran 2 non-parametric tests: a Mann-Whitney U and a Wilcoxon Signed Rank test.

I have read that using Cohen's D as an effect size for such tests is not suitable? Assuming that this is correct I have calculated effect sizes using the Z statistic (Z/sqrt of N).

However, once I now have this I am trying to calculate the power? I have tried to use G Power analysis but I think that it assumes the effect size I am entering Cohen's D?

If it is not possible through G.Power. I have been looking for any code on R that would allow me to do this?

Any help would be great! Thanks :)

  • $\begingroup$ "a Mann-Whitney U and a Wilcoxon Signed Rank test" cannot both be suitable for the same hypothesis and data. Do you have dependent samples or not? $\endgroup$ – Glen_b Mar 5 at 17:36
  • $\begingroup$ Sorry, I should have clarified - I have a mixed design where one variable is independent samples and the other variable is dependent samples. I have 2 hypotheses - so I have done one test for each $\endgroup$ – Charlotte Mar 5 at 18:51
  • 1
    $\begingroup$ Please edit to make that clear in the body of the question. $\endgroup$ – Glen_b Mar 5 at 21:42

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.