Various optimality criteria for the prediction of individual response curves

被引:8
|
作者
Prus, Maryna [1 ]
机构
[1] Otto von Guericke Univ, Inst Math Stochast, PF 4120, D-39016 Magdeburg, Germany
关键词
Random coefficients regression; Mixed models; Kiefer's criteria; E- and G-optimality; Individual parameters; Prediction; OPTIMAL DESIGNS; EQUIVALENCE;
D O I
10.1016/j.spl.2018.10.022
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 optimal designs for the Kiefer's criteria, which include the E-criterion as a particular case, and the G-criterion for the prediction in random coefficients regression (RCR) models. We obtain general the Kiefer's criteria for approximate designs and prove the equivalence of the E-criteria in the fixed effects and RCR models. We discuss in detail the G-criterion for ordinary linear regression on specific design regions. (C) 2018 Elsevier B.V. All rights reserved.
引用
收藏
页码:36 / 41
页数:6
相关论文
共 50 条