Robust estimation in multiple linear regression model with non-Gaussian noise

被引：30
作者：
Akkaya, Aysen D. [1 ]
Tiku, Moti L. [1 ]
机构：
[1] Middle E Tech Univ, Dept Stat, TR-06531 Ankara, Turkey
来源：
AUTOMATICA | 2008年 / 44卷 / 02期
关键词：
linear regression; robustness; data anomaly; modified maximum likelihood; outliers;
D O I：
10.1016/j.automatica.2007.06.029
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
The traditional least squares estimators used in multiple linear regression model are very sensitive to design anomalies. To rectify the situation we propose a reparametrization of the model. We derive modified maximum likelihood estimators and show that they are robust and considerably more efficient than the least squares estimators besides being insensitive to moderate design anomalies. (C) 2007 Elsevier Ltd. All rights reserved.
引用
收藏
页码：407 / 417
页数：11
相关论文
共 36 条
[1]  
ABROMOWITZ M, 1985, HDB MATH FUNCTIONS
[2]   Robust estimation and hypothesis testing under short-tailedness and inliers [J].
Akkaya, AD ;
Tiku, ML .
TEST, 2005, 14 (01) :129-150
[3]   MAXIMUM-LIKELIHOOD AND PREDICTION ERROR METHODS [J].
ASTROM, KJ .
AUTOMATICA, 1980, 16 (05) :551-574
[4]  
Atkinson A.C., 2000, SPR S STAT, DOI 10.1007/978-1-4612-1160-0
[5]   THE ASYMPTOTICS OF MAXIMUM-LIKELIHOOD AND RELATED ESTIMATORS BASED ON TYPE-II CENSORED-DATA [J].
BHATTACHARYYA, GK .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1985, 80 (390) :398-404
[6]   KINETICS OF CATALYTIC ISOMERIZATION OF NORMAL-PENTANE [J].
CARR, NL .
INDUSTRIAL AND ENGINEERING CHEMISTRY, 1960, 52 (05) :391-396
[7]   Identifiability and identification of chaotic systems based on adaptive synchronization [J].
Dedieu, H ;
Ogorzalek, MJ .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1997, 44 (10) :948-962
[8]  
Draper N., 2014, Applied Regression Analysis
[9]  
HAMILTON L. C., 1992, Regression with Graphics: A Second Course in Applied Statistics
[10]   ON THE DISTRIBUTION OF THE EXPECTED VALUES OF THE ORDER STATISTICS [J].
HOEFFDING, W .
ANNALS OF MATHEMATICAL STATISTICS, 1953, 24 (01) :93-100
1234