International Journal of Mathematics and Mathematical Sciences
Volume 7 (1984), Issue 2, Pages 407-408
doi:10.1155/S0161171284000429
Separation metrics for real-valued random variables
Michael D. Taylor
Department of Mathematics, University of Central Florida, Orlando 32816, Florida, USA
Abstract
If W is a fixed, real-valued random variable, then there are simple and easily satisfied conditions under which the function dW, where dW(X,Y)= the probability that W “separates” the real-valued random variables X and Y, turns out to be a metric. The observation was suggested by work done in [1].