I am writing a meta-analysis looking at the correlation between different tests for assessing body composition.

The results of the studies that I have included use different ways to calculate the correlation, including linear regression ($R^{2}$), Pearson's $r$, concordance correlation coefficient (CCC), and mean difference (SD) + 95% CI.

I would like to compare these results. I have found that I can take $\sqrt{R^{2}}$ to get $r$. Is there also a way to calculate $r$ from CCC? Or is CCC so similar to Pearson's $r$, that I can just call it $r$ and throw everything on one pile?

  • $\begingroup$ R-square and correlation are two versions of the same idea for a bivariate relationship; that's not a discovery, but a consequence of definitions. Otherwise these are different measures answering different questions. It is quite possible to get Pearson correlation and concordance correlation that are almost completely different. For example if $y \approx bx$ where $b \gg 0$ then correlation will be close to 1 but concordance correlation will be close to 0. $\endgroup$
    – Nick Cox
    Oct 17, 2018 at 16:26

1 Answer 1


Pearson's r measures linearity, while CCC measures agreement. Imagine a scatterplot between the two measures. High agreement implies that the scatterplot points are close to the 45 degrees line of perfect concordance which runs diagonally to the scatterplot, whereas a high Pearson's r implies that the scatterplot points are close to any straight line.

In practice,

CCC = r * C_b 

where r is Pearson's r, and C_b is a bias correction factor.

Therefore, CCC cannot be compared to Pearson's r. To calculate Pearson's r from CCC for a direct comparison you will need to divide CCC by C_b.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.