Recommendations on the Use of Bayesian Optimal Designs for Choice Experiments

被引：30

作者：

Kessels, Roselinde

Jones, Bradley ^{[2
]}

Goos, Peter ^{[1
]}

Vandebroek, Martina ^{[3
]}

机构：

[1] Univ Antwerp, Fac Appl Econ, B-2000 Antwerp, Belgium

[2] SAS Inst, Cary, NC USA

[3] Katholieke Univ Leuven, Louvain, Belgium

来源：

QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL | 2008年 / 24卷 / 06期

关键词：

choice experiments; Bayesian optimal designs; prior Parameter distribution; utility-neutral optimal designs;

D O I：

10.1002/qre.953

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

In this paper, we argue that some of the prior parameter distributions used ill the literature for the construction of Bayesian optimal designs for choice experiments are internal v inconsistent. lilt, provide practical advice oil how to properly specify the prior parameter distribution. Also, we present all example to illustrate that Bayesian optimal designs generally outperform utility-neutral optimal designs that are based oil linear design principles. Copyright (C) 2008 John Wiley & Sons, Ltd.

引用

页码：737 / 744

页数：8

共 16 条

[1] Optimal designs for 2k choice experiments [J].