Please use this identifier to cite or link to this item:
https://elib.bsu.by/handle/123456789/339983| Title: | A two-sample test based on multivariate ranks |
| Authors: | Pastukhov, N. V. |
| Keywords: | ЭБ БГУ::ЕСТЕСТВЕННЫЕ И ТОЧНЫЕ НАУКИ::Математика |
| Issue Date: | 2025 |
| Publisher: | Minsk : BSU |
| Citation: | Computer Data Analysis and Modeling: Stochastics and Data Science : Proc. of the XIV Intern. Conf., Minsk, Sept. 24–27, 2025 / Belarusian State Univ. ; eds.: Yu. Kharin (ed.-in-chief) [et al.]. – Minsk : BSU, 2025. – Pp. 207-209. |
| Abstract: | The paper investigates a two-sample test based on multivariate ranks. Using the multivariate rank map, we transport the initial sample onto a polar grid. Then we find the polar ray with the maximal number of points of the first sample. Using it, we construct the test statistic. A limit theorem for this statistic is proved, and a Poisson approximation is established via Sevastyanov theorem. Finally, the proposed test is compared against existing multivariate two-sample tests |
| URI: | https://elib.bsu.by/handle/123456789/339983 |
| ISBN: | 978-985-881-830-2 |
| Licence: | info:eu-repo/semantics/restrictedAccess |
| Appears in Collections: | 2025. Computer Data Analysis and Modeling: Stochastics and Data Science |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 207-209.pdf | 331,03 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.