Interpreting Rank Biserial Correlation
Hi team!
I am using non-parametric paired samples t-test and, consequently, get the Rank Biserial Correlation as effect size. I have no clue how to intepret this, and can find nothing I can follow online. I understand that a negative value is evidence against the alternative hypothesis, is that so? And how about the positive values? Is there any direction as to what is small, moderate, large effect size?
Thanks!
Georgios.
Comments
Just like any correlation:
You can read more about it here: https://easystats.github.io/effectsize/reference/rank_biserial.html
and a good paper: https://doi.org/10.2466%2F11.IT.3.1
For an intuitive interpretation see also the text above Eq 8 in this paper: https://www.tandfonline.com/doi/full/10.1080/02664763.2019.1709053
E.J.