Article information

2009 , Volume 14, ¹ 4, p.16-27

Denisov V.I., Timofeev V.S., Schekoldin V.Y.

An application of the canonical moments theory to estimation of the random variable density distributed over finite interval

An identification problem for random variables distributed over finite intervals is considered. A decomposition of the density function for the required random variable into series on orthogonal polynomials is obtained. The decomposition is made on the basis of the canonical moments theory, and the family of beta-distributions as a base density is used. An algorithm for estimation of the density function of a random variable distributed over a finite interval is proposed. Results of the application of the estimation algorithm for some distributions are presented.

[full text]
Keywords: random variable, distribution density estimation, canonical moments, orthogonal expansion, beta-distribution

Author(s):
Denisov Vladimir Ivanovitch
Dr. , Professor
Position: Councilor
Office: Novosibirsk State Technical University
Address: Russia, Novosibirsk, Marx avenue, 20
Phone Office: (383) 349-59-43
E-mail: videnis@nstu.ru

Timofeev Vladimir Semenovitch
Dr. , Associate Professor
Position: Professor
Office: Novosibirsk State Technical University
Address: Russia, Novosibirsk, Marx avenue, 20
Phone Office: (383) 346-31-72
E-mail: v.timofeev@corp.nstu.ru

Schekoldin Vladislav Yurjevitc
PhD. , Associate Professor
Position: Associate Professor
Office: Novosibirsk State Technical University
Address: Russia, Novosibirsk, Marx avenue, 20
Phone Office: (383) 346-31-72
E-mail: raix@ngs.ru


Bibliography link:
Denisov V.I., Timofeev V.S., Schekoldin V.Y. An application of the canonical moments theory to estimation of the random variable density distributed over finite interval // Computational technologies. 2009. V. 14. ¹ 4. P. 16-27
Home| Scope| Editorial Board| Content| Search| Subscription| Rules| Contacts
ISSN 1560-7534
© 2024 FRC ICT