Heteroscedastic nonlinear regression models based on scale mixtures of skew-normal distributions

被引：16

作者：

Lachos, Victor H. ^{[2
]}

Bandyopadhyay, Dipankar ^{[1
]}

Garay, Aldo M. ^{[2
]}

机构：

[1] Med Univ S Carolina, Dept Med, Div Biostat & Epidemiol, Charleston, SC 29425 USA

[2] Univ Estadual Campinas, Dept Estat, BR-13081970 Campinas, SP, Brazil

来源：

STATISTICS & PROBABILITY LETTERS | 2011年 / 81卷 / 08期

基金：

巴西圣保罗研究基金会;

关键词：

EM algorithm; Homogeneity; Nonlinear regression models; Scale mixtures; Skew-normal; MAXIMUM-LIKELIHOOD; DIAGNOSTICS;

D O I：

10.1016/j.spl.2011.03.019

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：

An extension of some standard likelihood based procedures to heteroscedastic nonlinear regression models under scale mixtures of skew-normal (SMSN) distributions is developed. We derive a simple EM-type algorithm for iteratively computing maximum likelihood (ML) estimates and the observed information matrix is derived analytically. Simulation studies demonstrate the robustness of this flexible class against outlying and influential observations, as well as nice asymptotic properties of the proposed EM-type ML estimates. Finally, the methodology is illustrated using an ultrasonic calibration data. (C) 2011 Elsevier B.V. All rights reserved.

引用

页码：1208 / 1217

页数：10

共 25 条

[1]

[Anonymous], 1993, BIOMETRIKA

[2]

[Anonymous], 1994, BIOMETRIKA

[3] Robust mixture modeling based on scale mixtures of skew-normal distributions [J].

Basso, Rodrigo M. ;

Lachos, Victor H. ;

Barbosa Cabral, Celso Romulo ;

Ghosh, Pulak .

COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2010, 54 (12) :2926-2941

[4] A general class of multivariate skew-elliptical distributions [J].

Branco, MD ;

Dey, DK .

JOURNAL OF MULTIVARIATE ANALYSIS, 2001, 79 (01) :99-113

[5] A nonlinear regression model with skew-normal errors [J].

Cancho, Vicente G. ;

Lachos, Victor H. ;

Ortega, Edwin M. M. .

STATISTICAL PAPERS, 2010, 51 (03) :547-558

[6]

Chwirut D., 1979, ULTRASONIC REFERENCE

[7] Corrected maximum likelihood estimators in heteroscedastic symmetric nonlinear models [J].

Cysneiros, F. J. A. ;

Cordeiro, G. M. ;

Cysneiros, A. H. M. A. .

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 2010, 80 (04) :451-461

[8] Residuals and their statistical properties in symmetrical nonlinear models [J].

Cysneiros, Francisco Jose A. ;

Vanegas, Luis Hernando .

STATISTICS & PROBABILITY LETTERS, 2008, 78 (18) :3269-3273

[9] MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].

DEMPSTER, AP ;

LAIRD, NM ;

RUBIN, DB .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38

[10] Multivariate student-t regression models:: Pitfalls and inference [J].

Fernandez, C ;

Steel, MFJ .

BIOMETRIKA, 1999, 86 (01) :153-167

← 1 2 3 →