On estimating linear relationships when both variables are subject to heteroscedastic measurement errors

被引：56

作者：

Cheng, Chi-Lun ^{[1
]}

Riu, Jordi

机构：

[1] Acad Sinica, Inst Stat Sci, Taipei 115, Taiwan

[2] Univ Rovira & Virgili, Dept Analyt & Organ Chem, Tarragona 43007, Catalonia, Spain

来源：

TECHNOMETRICS | 2006年 / 48卷 / 04期

关键词：

generalized least squares; heteroscedastic measurement error; large-sample theory; maximum likelihood estimation; measurement error model; method-of-moments estimate;

D O I：

10.1198/004017006000000237

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：

This article discusses point estimation of the parameters in a linear measurement error (errors in variables) model when the variances in the measurement errors on both axes vary between observations. A compendium of existing and new regression methods is presented. Application of these methods to real data cases shows that the coefficients of the regression lines depend on the method selected. Guidelines for choosing a suitable regression method are provided.

引用

页码：511 / 519

页数：9

共 23 条

[1]

Adcock R., 1877, ANALYST, V4, P183

[2]

Bartholomew D. J., 1999, LATENT VARIABLE MODE

[3] NOTE ON MAXIMUM-LIKELIHOOD ESTIMATION OF LINEAR STRUCTURAL RELATIONSHIP [J].