\rho_F(x,y) = \frac{1}{n} \sum_{i=1}^n {\rm sgn}(x_i - \bar x) \cdot {\rm sgn}(y_i - \bar y) = \frac{C - H}{ C + H} 

where  and

 — number of pairs with the same sign of deviation from the mean value 

  — number of pairs with the opposite sign of deviation from the mean value  


The Kendall correlation coefficient is similar to Spearmen correlation coefficient in nature but sometimes has advantage by a more reliable pick up a correlation in noisy data.

See also


Formal science / Mathematics / Statistics Statistical correlation 

Statistical correlation metrics @ review ] [ Pearson correlation ] [ Spearmen Correlation ] [ Kendall correlation ]