fasano.franceschini.test: An Implementation of a Multidimensional KS Test in R

TL;DR

This paper introduces an R package implementing a multidimensional Kolmogorov-Smirnov test, enabling efficient comparison of complex distributions across various data types and dimensions.

Contribution

It provides a computationally efficient, versatile R implementation of a multidimensional KS test based on Fasano and Franceschini's method, extending the applicability of the KS test.

Findings

The package performs competitively with similar R tools.

It is applicable to data of any dimension and type.

The implementation is computationally efficient.

Abstract

The Kolmogorov-Smirnov (KS) test is a nonparametric statistical test used to test for differences between univariate probability distributions. The versatility of the KS test has made it a cornerstone of statistical analysis across many scientific disciplines. However, the test proposed by Kolmogorov and Smirnov does not easily extend to multidimensional distributions. Here we present the fasano.franceschini.test package, an R implementation of a multidimensional two-sample KS test described by Fasano and Franceschini (1987). The fasano.franceschini.test package provides a test that is computationally efficient, applicable to data of any dimension and type (continuous, discrete, or mixed), and that performs competitively with similar R packages.