Number of Distinct Values in a Large Sample with Dependent Observations under fGn from an Infinite Discrete Distribution | Sciact - Система учета научной деятельности ИМ СО РАН

Number of Distinct Values in a Large Sample with Dependent Observations under fGn from an Infinite Discrete Distribution Научная публикация

Журнал

Сибирские электронные математические известия (Siberian Electronic Mathematical Reports)
, E-ISSN: 1813-3304

Вых. Данные

Год: 2026, Том: 23, Номер: 1, Страницы: 393–403 Страниц : 11 DOI: 10.33048/semi.2026.23.025

Ключевые слова

urn scheme, fractional noise, transform of Gaussian sequence, long-range dependence, statistical text modeling.

Авторы

Arkashov N.S. ¹

Организации

1	Sobolev Institute of Mathematics

Информация о финансировании (1)

Институт математики им. С.Л. Соболева СО РАН

FWNF-2024-0001

The growth dynamics of the number of distinct values in samples obtained from a stationary sequence of dependent observations with an infinite discrete distribution is investigated. The analysis of this behavior for samples formed from a sequence of i.i.d. random variables is well-established. In this paper, the expected number of distinct values in the independent case is compared with that for dependent observations. A connection is established between the estimation of these expectations and the problem of estimating multivariate normal distributions. The application of the considered stationary sequences to statistical text modeling is discussed.

Arkashov N.S.
Number of Distinct Values in a Large Sample with Dependent Observations under fGn from an Infinite Discrete Distribution
Сибирские электронные математические известия (Siberian Electronic Mathematical Reports). 2026. V.23. N1. P.393–403. DOI: 10.33048/semi.2026.23.025

Поступила в редакцию:	11 дек. 2025 г.
Опубликована online:	20 апр. 2026 г.

Нет идентификаторов