Wilcoxon Test
Categories: Metrics, Financial Theory
The Wilcoxon Test, a.k.a. the Wilcoxon signed-rank test, is a statistical method that calculates the differences between two paired groups. Unlike other statistical tests, the Wilcoxon Test is nonparametric, which means there are no parameters with underlying assumptions (for instance, even your basic mean and variance are parameters).
Still, the Wilcoxon Test does require some assumptions...namely that the data points are paired and come from the same population, and that each pair is random and independent.
The Wilcoxon Test is a great alternative to your typical statistical t-test for matched pairs when the population isn’t assumed to be normally distributed (if you didn’t know: a normal distribution is that nice bell curve shape, which a lot of statistical methods use as a base assumption).