An algorithm of distance correlation and its comparision with Pearson correlation on samples
For scalar random variables X&Y and real numbers a&b,
- dCor(aX+bY) = dCor(X,Y), a != 0.
- 0 <= dCor(X,Y) <= 1.
- dCor(X,Y) = 0 iff X&Y are independent.
https://www.stat.cmu.edu/~ryantibs/datamining/lectures/12-cor3-marked.pdf