Not OK. The Spearman correlation operates on ranks and so artificially constrains variation. Nor has it any real-life interpretation that I have been able to discover.

Kendall's tau-b has at least a potential interpretation. It is based on the number of pairs of observations that are positively correlated (that is, the higher observation on variable 1 is also the higher on variable 2). To retrieve this information, you need to undo the last two steps of the calculation

- Add 1 to the correlation (which rescales it between zero and 2

- divide by 2 (which rescales it between zero and 1)

This figure is the percentage of positively correlated pairs. You can see that if there is no correlation, this is 50%, and it's minimum and maximum are zero and one. The two transformations above are to make the scale two units wide (multiply by two) and to make the range run from –1 to+1 (subtract one).

Thank you SO MUCH Ronán Michael Conroy :-) This element is not crystal clear in the litterature I read and chatGPT gives me a wrong answer about this. Best regards, professor

Spearman’s rank correlation coefficient, also known as Spearman’s rho, is a non-parametric measure of rank correlation that assesses the strength and direction of the monotonic relationship between two variables. While it is common to square Pearson’s correlation coefficient to obtain the coefficient of determination (R2), which represents the proportion of variance in one variable that can be explained by the other variable, it is not customary to square Spearman’s rho. Squaring Spearman’s rho would represent the proportion of shared variance in the two ranked variables, but it is not a common practice and may not provide a meaningful interpretation of the data. Instead, Spearman’s rho itself can be used as a measure of effect size to represent the strength of the relationship between two variables.