Jeffries-Matusita Distance

The Jeffries-Matusita distance function computes class separability between two sets of data based on their probability distributions.

The Jeffries-Matusita Distance function computes the statistical measure of dissimilarity or separability between two sets of data based on their probability distributions. It is particularly useful in classification tasks to assess the separation between classes or the discriminative power of features. This distance measure ranges from 0 (indicating maximum overlap or similarity) to sqrt(2) (indicating complete separation). The function can help users evaluate the effectiveness of feature selection or dimensionality reduction techniques in enhancing class separability.