SEQUENTIAL EMPIRICAL BAYESIAN DESIGN FOR SENSITIVITY EXPERIMENTS

Maximum likelihood recursions were used by Wu （1985） to estimate extreme quantiles of a quantal response curve. For certain choices of initial designs, Wu＇s method performs well. In many fields of application, there often exist some different initial designs which are known as the up-and- down desig...

Full description

Saved in:
Bibliographic Details
Published inJournal of systems science and complexity Vol. 24; no. 5; pp. 955 - 968
Main Authors Tian, Yubin, Fang, Yongfei, Wang, Dianpeng
Format Journal Article
LanguageEnglish
Published Beijing Academy of Mathematics and Systems Science, Chinese Academy of Sciences 01.10.2011
Subjects
Complex Systems
Control
Mathematics
Mathematics and Statistics
Mathematics of Computing
Operations Research/Decision Theory
Statistics
Systems Theory
分位数
初始设计
响应曲线
序贯
敏感性试验
测试数据
知识信息
贝叶斯
sequential design
extreme quantiles
Bayesian strategy
bootstrap principle
Online AccessGet full text

Cover

More Information
Summary:Maximum likelihood recursions were used by Wu （1985） to estimate extreme quantiles of a quantal response curve. For certain choices of initial designs, Wu＇s method performs well. In many fields of application, there often exist some different initial designs which are known as the up-and- down designs. Based on the existing data set from such a design, the authors propose three sequential empirical Bayesian designs by quickly and efficiently exploiting the information in the testing data and known knowledge. The improvement obtained by using the new procedures for the estimation of extreme quantiles is substantial.
Bibliography:11-4543/O1
Bayesian strategy, bootstrap principle, extreme quantiles, sequential design.
Maximum likelihood recursions were used by Wu （1985） to estimate extreme quantiles of a quantal response curve. For certain choices of initial designs, Wu＇s method performs well. In many fields of application, there often exist some different initial designs which are known as the up-and- down designs. Based on the existing data set from such a design, the authors propose three sequential empirical Bayesian designs by quickly and efficiently exploiting the information in the testing data and known knowledge. The improvement obtained by using the new procedures for the estimation of extreme quantiles is substantial.
ISSN:1009-6124
1559-7067
DOI:10.1007/s11424-011-8122-4