Mann-Whitney U test, effect size changed

General help and assistance with jamovi. Bug reports can be made at our issues page: https://github.com/jamovi/jamovi/issues . (If you're unsure feel free to discuss it here)

by luddew11 » Tue Oct 20, 2020 8:17 am

Hi!

When I performed an Mann-Whitney U test on some data I wanted to see the effect size, at first it was showed Cohen's d "0.06" and all was good but then I wanted to perform it again later on and now it's reported as "Rank biserial correlation" with an effect size as "0.03"... And I don't know what has changed it my data material. All that I can think of is that I changed the items to continous scale instead of ordinal scale. But when I change back to ordinal scale now it still report the effect size as "Rank biserial correlation"...

Anyone that can help me?
luddew11
 
Posts: 2
Joined: Tue Oct 20, 2020 8:03 am

by Ravi » Tue Oct 20, 2020 8:24 am

Did you by any chance updated jamovi in the meantime? We recently updated the effect sizes in the t-tests to use more appropriate types of effect sizes for different tests. In this update we changed the effect size of the mann-whitney U test from cohen's d to a rank biserial correlation (which is more appropriate in this case).
User avatar
Ravi
 
Posts: 154
Joined: Sat Jan 28, 2017 11:18 am

by luddew11 » Tue Oct 20, 2020 8:31 am

Oh! Yeah I can see now when we started I used the 1.1.9.0 version and now the Jamovi version 1.2.27.0. It must have updated without me noticing. Thank you for your answer!!!
luddew11
 
Posts: 2
Joined: Tue Oct 20, 2020 8:03 am


Return to Help