ROBUST ESTIMATION FOR ARMA MODELS

被引：50

作者：

Muler, Nora ^{[1
]}

Pena, Daniel ^{[2
]}

Yohai, Victor J.

机构：

[1] Univ Torcuata Tella, Dept Math & Estadist, RA-1428 Buenos Aires, DF, Argentina

[2] Univ Carlos III Madrid, Dept Estadist, Madrid 28903, Spain

来源：

ANNALS OF STATISTICS | 2009年 / 37卷 / 02期

关键词：

MM-estimates; outliers; time series; TIME-SERIES; INFINITE VARIANCE; OUTLIERS; PARAMETERS;

D O I：

10.1214/07-AOS570

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

This paper introduces a new class of robust estimates for ARMA models. They are M-estimates, but the residuals are computed so the effect of one outlier is limited to the period where it occurs. These estimates are closely related to those based on a robust filter, but they have two important advantages: they are consistent and the asymptotic theory is tractable. We perform a Monte Carlo where we show that these estimates compare favorably with respect to standard M-estimates and to estimates based on a diagnostic procedure.

引用

页码：816 / 840

页数：25

共 25 条

[1]

Bianco A. M., 1996, COMPSTAT. Proceedings in Computational Statistics. 12th Symposium, P27

[2]

BRUBACHER SR, 1974, TIME SERIES OUTLIER

[3] ROBUST ESTIMATES FOR ARMA MODELS [J].

BUSTOS, OH ;

YOHAI, VJ .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1986, 81 (393) :155-168

[4] ESTIMATION OF TIME-SERIES PARAMETERS IN THE PRESENCE OF OUTLIERS [J].

CHANG, I ;

TIAO, GC ;

CHEN, C .

TECHNOMETRICS, 1988, 30 (02) :193-204

[5] JOINT ESTIMATION OF MODEL PARAMETERS AND OUTLIER EFFECTS IN TIME-SERIES [J].

CHEN, C ;

LIU, LM .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1993, 88 (421) :284-297

[6]

Davidson James, 1994, Stochastic Limit Theory: An Introduction for Econometricians

[7] Gauss-Newton and M-estimation for ARMA processes with infinite variance [J].

Davis, RA .

STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 1996, 63 (01) :75-95

[8] M-ESTIMATION FOR AUTOREGRESSIONS WITH INFINITE VARIANCE [J].

DAVIS, RA ;

KNIGHT, K ;

LIU, J .

STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 1992, 40 (01) :145-180

[9]

FOX AJ, 1972, J ROY STAT SOC B, V34, P350

[10] Comprehensive definitions of breakdown points for independent and dependent observations [J].

Genton, MG ;

Lucas, A .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2003, 65 :81-94

← 1 2 3 →