Optimal designs for regression models with autoregressive errors

被引：0

作者：

Dette, Holger ^{[1
]}

Pepelyshev, Andrey ^{[2
,3
]}

Zhigljaysky, Anatoly ^{[2
,4
]}

机构：

[1] Ruhr Univ Bochum, Fak Math, D-44780 Bochum, Germany

[2] Cardiff Univ, Sch Math, Cardiff CF24 4AG, S Glam, Wales

[3] St Petersburg State Univ, Fac Math & Mech, St Petersburg 199034, Russia

[4] Lobachevskii Nizhnii Novgorod State Univ, Nizhnii Novgorod, Nizhny Novgorod, Russia

来源：

STATISTICS & PROBABILITY LETTERS | 2016年 / 116卷

基金：

俄罗斯科学基金会; 美国国家卫生研究院;

关键词：

Linear regression; Correlated-observations; Signed measures; Optimal design; BLUE; Continuous autoregressive model; CORRELATED ERRORS; LINEAR-MODELS; TIME;

D O I：

10.1016/j.spl.2016.04.008

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 the one-parameter regression model with AR(1) and AR(2) errors we find explicit expressions and a continuous approximation of the optimal discrete design for the signed least square estimator. The results are used to derive the optimal variance of the best linear estimator in the continuous time model and to construct efficient estimators and corresponding optimal designs for finite samples. (C) 2016 Elsevier B.V. All rights reserved.

引用

页码：107 / 115

页数：9

共 18 条

[1]

[Anonymous], 1987, Journal of Time Series Analysis, DOI [10.1111/j.1467-9892.1987.tb00439.x, DOI 10.1111/J.1467-9892.1987.TB00439.X]

[2] ROBUSTNESS OF DESIGN AGAINST AUTOCORRELATION IN TIME .1. ASYMPTOTIC THEORY, OPTIMALITY FOR LOCATION AND LINEAR-REGRESSION [J].