2

I am working on my thesis and my supervisor wanted me to calculate cohen's d for my significant results. I am using SPSS and I was able to calculate Cohen's d using an external site. My independent variable is group (HRD or NRD). I was able to enter in the means and standard deviations for my two groups into this site to get the Cohen's d (as it is not possible to do so on SPSS). I have two results that are significant, however I calculated them using independent Mann Whitney U tests and the results I have only provide one mean and one SD.

I was just wondering if it is at all possible to calculate Cohen's d from nonparametric statistics.

gung - Reinstate Monica
  • 132,789
  • 81
  • 357
  • 650
Audrey H
  • 21
  • 2
  • I've seen previous threads attempt at answering this question as well, such as http://stats.stackexchange.com/questions/133077/effect-size-to-wilcoxon-signed-rank-test. But It doesn't seem to be a toolbox of nonparametric effect size measurements to use. A professor once told me to bootstrap Cohen's D. – Jon Dec 09 '16 at 16:56

0 Answers0