Open access
Date
2022-06Type
- Journal Article
Abstract
Following the line of classification-based two-sample testing, tests based on the Random Forest classifier are proposed. The developed tests are easy to use, require almost no tuning, and are applicable for any distribution on Rd. Furthermore, the built-in variable importance measure of the Random Forest gives potential insights into which variables make out the difference in distribution. An asymptotic power analysis for the proposed tests is conducted. Finally, two real-world applications illustrate the usefulness of the introduced methodology. To simplify the use of the method, the R-package “hypoRF” is provided. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000530959Publication status
publishedExternal links
Journal / series
Computational Statistics & Data AnalysisVolume
Pages / Article No.
Publisher
ElsevierSubject
Random forest; Distribution testing; Classification; Kernel two-sample test; MMD; Total variation distance; U-statisticsMore
Show all metadata