SEQUENTIAL EMPIRICAL BAYESIAN DESIGN FOR SENSITIVITY EXPERIMENTS

作     者：Yubin TIAN Yongfei FANG Dianpeng WANG 

作者机构：Department of Mathematics Beijing Institute of Technology Beijing 100081 China 

出 版 物：《Journal of Systems Science & Complexity》 (系统科学与复杂性学报（英文版）)

年 卷 期：2011年第24卷第5期

页      面：955-968页

核心收录：

学科分类：02[经济学] 0202[经济学-应用经济学] 020208[经济学-统计学] 07[理学] 08[工学] 080402[工学-测试计量技术及仪器] 0804[工学-仪器科学与技术] 0714[理学-统计学（可授理学、经济学学位）] 070103[理学-概率论与数理统计] 0701[理学-数学] 

基　　金：This research is supported by the National Natural Science Foundation of China under Grant No. 10971012 

主　　题：Bayesian strategy bootstrap principle extreme quantiles sequential design. 

摘      要：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.