On maximin designs for correlated observations

被引：13

作者：

Bischoff, W ^{[1
]}

机构：

[1] UNIV KARLSRUHE,INST MATH STOCHAST,D-76128 KARLSRUHE,GERMANY

来源：

STATISTICS & PROBABILITY LETTERS | 1996年 / 26卷 / 04期

关键词：

linear model; correlated observations; maximin designs; D-criterion; tridiagonal matrices as covariance structure;

D O I：

10.1016/0167-7152(95)00032-1

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 linear model, we consider the problem of finding optimal or efficient designs with respect to the D-criterion when the covariance matrix is an unknown element of a class C. In general, designs that are efficient for each C epsilon C do not exist. Therefore, maximin designs are of interest. These designs maximize the minimal efficiency where the minimum is taken over all possible covariance matrices and the maximum is taken over all feasible designs. Efficient maximin designs are derived for tridiagonal covariance matrices.

引用

页码：357 / 363

页数：7