Can Cohen's d be used for distributions that are not normal?

Can Cohen's d be used for distributions that are not normal? Or is it used only to compare normal distributions?

asked Jul 26, 2017 at 15:14 207 3 3 silver badges 12 12 bronze badges

1 Answer 1

$\begingroup$

You can do anything. The question is whether it would make sense. When the mean difference would be a poor reflection of the difference between groups, Cohen's d will also fail.

There are modifications to Cohen's d that you can use in such instances and other instances when Cohen's d would be problematic. Algina and co have some suggestions https://www.ncbi.nlm.nih.gov/pubmed/26487051

answered Jul 26, 2017 at 16:59 Heteroskedastic Jim Heteroskedastic Jim 5,205 1 1 gold badge 17 17 silver badges 40 40 bronze badges

Linked

Related

Hot Network Questions

Subscribe to RSS

Question feed

To subscribe to this RSS feed, copy and paste this URL into your RSS reader.

Site design / logo © 2024 Stack Exchange Inc; user contributions licensed under CC BY-SA . rev 2024.9.17.15358