Equalities between OLSE, BLUE and BLUP in the linear model

被引:20
作者
Haslett, Stephen J. [1 ]
Isotalo, Jarkko [2 ]
Liu, Yonghui [3 ]
Puntanen, Simo [4 ]
机构
[1] Massey Univ, Inst Fundamental Sci, Palmerston North, New Zealand
[2] Univ Helsinki, Dept Forest Sci, FIN-00014 Helsinki, Finland
[3] Shanghai Finance Univ, Dept Appl Math, Shanghai 201209, Peoples R China
[4] Univ Tampere, Sch Informat Sci, Tampere 33014, Finland
关键词
Best linear unbiased estimator; Best linear unbiased predictor; Gauss-Markov model; Generalized inverse; Linear model; Ordinary least squares; SMALL-AREA ESTIMATION; LEAST-SQUARES; UNBIASED PREDICTOR; SPATIAL-PATTERNS; EUCLIDEAN NORM; RURAL POVERTY; SIMPLE FORMS; DIFFERENCE; ESTIMATORS; MATRIX;
D O I
10.1007/s00362-013-0500-7
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 equalities between the ordinary least squares estimator (), the best linear unbiased estimator () and the best linear unbiased predictor () in the general linear model extended with the new unobservable future value of the response whose expectation is . Our aim is to provide some new insight and new proofs for the equalities under consideration. We also collect together various expressions, without rank assumptions, for the and provide new results giving upper bounds for the Euclidean norm of the difference between the and and between the and . A remark is made on the application to small area estimation.
引用
收藏
页码:543 / 561
页数:19
相关论文
共 45 条