On the asymptotic optimality of orthoregressional estimators

On the asymptotic optimality of orthoregressional estimators Full article

Journal

Journal of Applied and Industrial Mathematics
ISSN: 1990-4789 , E-ISSN: 1990-4797

Output data

Year: 2016, Volume: 10, Number: 4, Pages: 511-519 Pages count : 9 DOI: 10.1134/S1990478916040074

Tags

asymptotic efficiency; linear autonomous difference equation; orthoregressional estimator; parameter identification; STLS estimator

Authors

Lomov A.A. ^1,2

Affiliations

1	Sobolev Institute of Mathematics, pr. Akad. Koptyuga 4, Novosibirsk, 630090, Russian Federation
2	Novosibirsk State University, ul. Pirogova 2, Novosibirsk, 630090, Russian Federation

It is shown that the orthoregressional (STLS) parameter estimators in linear algebraic systems (including autonomous difference equations with matrix coefficients) converge to the maximum likelihood estimators and thus become asymptotically best in the limit case of large variances of the random coordinates on the variety of solutions to the system observed with additive random perturbations. © 2016, Pleiades Publishing, Ltd.

Lomov A.A.
On the asymptotic optimality of orthoregressional estimators
Journal of Applied and Industrial Mathematics. 2016. V.10. N4. P.511-519. DOI: 10.1134/S1990478916040074 Scopus OpenAlex

Ломов А.А.
Об асимптотической оптимальности орторегрессионных оценок
Сибирский журнал индустриальной математики. 2016. Т.19. №4(68). С.51-60. DOI: 10.17377/sibjim.2016.19.406

Scopus:	2-s2.0-84996587684
OpenAlex:	W2549429725

DB	Citing
Scopus	3
OpenAlex	2