Not logged in.

Contribution Details

Type Journal Article
Scope Discipline-based scholarship
Title On the use of random forest for two-sample testing
Organization Unit
  • Simon Hediger
  • Loris Michel
  • Jeffrey Näf
Item Subtype Original Work
Refereed Yes
Status Published in final form
  • English
Journal Title Computational Statistics & Data Analysis
Publisher Elsevier
Geographical Reach international
ISSN 0167-9473
Volume 170
Page Range 107435
Date 2022
Abstract Text 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 R^d. 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.
Free access at Official URL
Related URLs
Digital Object Identifier 10.1016/j.csda.2022.107435
Other Identification Number merlin-id:21963
PDF File Download from ZORA
Export BibTeX