Elliptical structural models

被引:15
作者
ArellanoValle, RB
Bolfarine, H
机构
[1] PONTIFICIA UNIV CATOLICA CHILE,SANTIAGO,CHILE
[2] UNIV SAO PAULO,DEPT ESTAT,IME,BR-05389970 SAO PAULO,BRAZIL
关键词
Bartlett corrections; dependent and independent structural elliptical models; information matrix; maximum likelihood estimators; orthogonal parameters; likelihood ratio test;
D O I
10.1080/03610929608831841
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
In this paper we consider structural measurement error models within the elliptical family of distributions. We consider dependent and independent elliptical models, each of which requires special treatment methodology. We discuss in each case estimation and hypothesis testing using maximum likelihood theory. As shown, most of the developments obtained under normal theory carries through to the dependent case. In the independent case, emphasis is placed on the t-distribution, an important member of the elliptical family. Correcting likelihood ratio statistics in both cases is also of major interest.
引用
收藏
页码:2319 / 2341
页数:23
相关论文
共 18 条
[1]   DISTRIBUTION OF THE CORRELATION-COEFFICIENT FOR THE CLASS OF BIVARIATE ELLIPTIC MODELS [J].
ALI, MM ;
JOARDER, AH .
CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE, 1991, 19 (04) :447-452
[2]  
ANDERSON TW, 1986, CANADIAN J STAT, V44, P55
[3]  
BOLFARINE H, 1993, ANN I STAT MATH, V3, P531
[4]  
CORDEIRO GM, 1983, J ROY STAT SOC B MET, V45, P404
[5]  
COX DR, 1987, J ROY STAT SOC B MET, V49, P1
[6]  
Fuller W. A., 2009, Measurement error models
[7]  
GOSH M, 1980, J MULTIVARIATE ANAL, V10, P332
[8]  
GRAYBILL FA, 1983, MATRICES APPLICATION
[9]   STATISTICAL-INFERENCE BASED ON PSEUDO-MAXIMUM LIKELIHOOD ESTIMATORS IN ELLIPTIC POPULATIONS [J].
KANO, Y ;
BERKANE, M ;
BENTLER, PM .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1993, 88 (421) :135-143
[10]   ROBUST STATISTICAL MODELING USING THE T-DISTRIBUTION [J].
LANGE, KL ;
LITTLE, RJA ;
TAYLOR, JMG .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1989, 84 (408) :881-896