An Efficient Method to Determine the Degree of Overlap of Two Multivariate Distributions
Assessing the degree to which two probability density functions overlap is an important problem in several applications. Most of the existing proposals to tackle this problem can only deal with univariate distributions. For multivariate problems, existing methods often rely on unrealistic parametric distributional assumptions or are such that the corresponding univariate marginal measures are combined using ad hoc procedures. In this paper, we propose a new empirical measure of the degree of overlap of two multivariate distributions. Our proposal makes no assumptions on the form of the densities and can be efficiently computed even in relatively high-dimensional problems.
KeywordsDistance matrix Crossmatch algorithm Multivariate analysis
The work of the first author was partially supported by the Sistema Nacional de Investigadores, Mexico. The authors are grateful for the comments and suggestions of the editor and two reviewers on an earlier version of the paper.
- 1.Arias-Castro, E., Pelletier, B.: On the consistency of the crossmatch test (2015). arXiv:1509.05790 [math.ST]
- 3.Gelman, A., Hill, J.: Data Analysis Using Regression and Multilevel/Hierarchical Models. Cambridge University Press, Cambridge (2007)Google Scholar
- 4.Heller, R., Small, D., Rosenbaum, P.: crossmatch: the cross-match test. R package version 1.3-1 (2012). https://CRAN.R-project.org/package=crossmatch
- 5.Meredith, M., Ridout, M.: Overlap: estimates of coefficient of overlapping for animal activity patterns. R package version 0.3.2 (2018). https://CRAN.R-project.org/package=overlap
- 7.R Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria (2018). https://www.R-project.org/