SEQUENTIAL EMPIRICAL BAYESIAN DESIGN FOR SENSITIVITY EXPERIMENTS

• 作 者: Yubin TIAN Yongfei FANG Dianpeng WANG
• 机 构: Department of Mathematics, Beijing Institute of Technology, Beijing 100081, China
• 出 处: 系统科学与复杂性学报（英文版）
• 发表日期: 2011年5期
• 关键词: 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.