Affordable Access

Access to the full text

Sequential empirical Bayesian design for sensitivity experiments

Authors
  • Tian, Yubin1
  • Fang, Yongfei1
  • Wang, Dianpeng1
  • 1 Beijing Institute of Technology, Department of Mathematics, Beijing, 100081, China , Beijing (China)
Type
Published Article
Journal
Journal of Systems Science and Complexity
Publisher
Academy of Mathematics and Systems Science, Chinese Academy of Sciences
Publication Date
Oct 04, 2011
Volume
24
Issue
5
Identifiers
DOI: 10.1007/s11424-011-8122-4
Source
Springer Nature
Keywords
License
Yellow

Abstract

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.

Report this publication

Statistics

Seen <100 times