ESTIMATION FOR 2-WAY ANALYSIS OF VARIANCE WITH CORRELATED ERRORS

被引：1

作者：

NGWENGWE, AM

MCCULLOCH, CE

机构：

[1] CORNELL UNIV,BIOMETR UNIT,ITHACA,NY 14853

[2] CORNELL UNIV,CTR STAT,ITHACA,NY 14853

来源：

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION | 1991年 / 20卷 / 01期

关键词：

CORRELATED ERRORS; INTRACLASS CORRELATION COEFFICIENT; LOG-LIKELIHOOD FUNCTION; MAXIMUM LIKELIHOOD ESTIMATOR; MEAN SQUARES; MIXED EFFECTS MODEL; MULTIVARIATE NORMAL; UNIFORM COVARIANCE STRUCTURE;

D O I：

10.1080/03610919108812955

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：

We consider some estimation and distribution problems encountered in a two way analysis of variance model with only one observation per cell, errors correlated in one level, and the variances are not necessarily equal. The independence criteria for the row and interaction mean sum of squares and distribution of the maximum likelihood estimator of the correlation coefficient are given.

引用

页码：325 / 339

页数：15

共 18 条

[1]

ABRAMOWITZ M, 1972, NBS APPLIED MATH SER, V55

[2] THE ESTIMATION OF RELIABILITY WHEN SEVERAL TRIALS ARE AVAILABLE [J].