G-optimal exact designs for quadratic regression

被引：1

作者：

Imhof, Lorens A. ^{[1
,2
]}

机构：

[1] Univ Bonn, Dept Stat, D-53113 Bonn, Germany

[2] Univ Bonn, Hausdorff Ctr Math, D-53113 Bonn, Germany

来源：

JOURNAL OF STATISTICAL PLANNING AND INFERENCE | 2014年 / 154卷

关键词：

Admissibility; Experimental design; Optimal design; Polynomial regression; LOG CONTRAST MODEL; POLYNOMIAL REGRESSION;

D O I：

10.1016/j.jspi.2014.03.008

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：

Exact experimental designs are presented that minimize the maximum variance of the best linear unbiased estimator of a quadratic regression function on an interval. The main result confirms a conjecture of Constantine, Lim and Studden, which is based on earlier computations of Gaffke and Krafft (Constantine et al. [1987. Admissible and optimal exact designs for polynomial regression. J. Statist. Plann. Inference 16, 15-32], Gaffke and Krafft [1982. Exact D-optimum designs for quadratic regression. J. Roy. Statist. Soc. Ser. B 44, 394-397]). (C) 2014 Elsevier B.V. All rights reserved.

引用

页码：133 / 140

页数：8

共 26 条

[1] alaevskii O.V., 1965, P STEKLOV I MATH, V79, P132
[2] [Anonymous], 1959, THEORY MATRICES
[3] Chang FC, 1998, STAT SINICA, V8, P527
[4] ADMISSIBLE AND OPTIMAL EXACT DESIGNS FOR POLYNOMIAL REGRESSION
CONSTANTINE, KB
LIM, YB
STUDDEN, WJ
[J]. JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1987, 16 (01) : 15 - 32
[5] Dette H, 2008, STAT SINICA, V18, P135
[6] Fedorov V., 1972, Theory of Optimal Experiment
[7] ON D-OPTIMALITY OF EXACT LINEAR-REGRESSION DESIGNS WITH MINIMUM SUPPORT
GAFFKE, N
[J]. JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1987, 15 (02) : 189 - 204
[8] GAFFKE N, 1982, J ROY STAT SOC B MET, V44, P394
[9] THE SPACING OF OBSERVATIONS IN POLYNOMIAL REGRESSION
GUEST, PG
[J]. ANNALS OF MATHEMATICAL STATISTICS, 1958, 29 (01): : 294 - 299
[10] EFFICIENCY PROBLEMS IN POLYNOMIAL ESTIMATION
HOEL, PG
[J]. ANNALS OF MATHEMATICAL STATISTICS, 1958, 29 (04): : 1134 - 1145

← 1 2 3 →