Optimal designs for comparing curves in heteroscedastic measurement error models

View at publisher Summarise with VIRAT
Authors: Min-Jue Zhang, Rong‐Xian Yue, Xueping Chen
Cited by: 0
References: 29

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

.This article is concerned with optimal designs of experiments for the comparison between measurement error models for two groups with heteroscedasticity. A novel approach is proposed to identify optimal designs for comparing the two curves in heteroscedastic measurement error models, which leads to non-convex optimization problems. Several necessary conditions are presented to portray the local μp-optimality of designs and the optimal allocation of sample size in each group by employing the corrected score function approach. The results are illustrated with examples modeling the dose response relationship. Numerical results show that the use of the proposed optimal designs, instead of commonly used non-optimal designs, yields a reduction of the width of the confidence band for the difference of the curves. Furthermore, it is observed that, for curve comparisons, the optimal design derived from the heteroscedastic measurement error model is more robust than that produced by the corresponding model assuming no measurement error.

Fields of Study & Subjects

Optimal Experimental Design Methods Statistical Methods in Clinical Trials Advanced Statistical Methods and Models

Publication details

Journal / source
Communication in Statistics- Theory and Methods
Volume
55
Issue
15
Pages
5079–5102
Publication date
25 March 2026
Language
EN