Bayes A-Optimal and Efficient Block Designs for Comparing Test Treatments with A Standard Treatment

John Stufken

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A sufficient condition for the Bayes A-optimality of block designs when comparing a standard treatment with v test treatments is given by Majumdar. (In: Optimal Design and Analysis of Experiments, Y. Dodge, V. V. Fedorov and H. P. Wynn (Eds.), 15–27, North-Holland, 1988). The priors that he considers depend on a constant a ε [0, ∞), with a - 0 corresponding to no prior information at all. The given sufficient condition, consequently, also depends on a. Large families of optimal and highly efficient designs are only known for the case a — 0. We will show how some of the results for a - 0 can be extended to obtain large families of optimal and highly efficient designs for arbitrary values of a. In addition, these results are useful when considering design robustness against an improper choice of a.

Original languageEnglish (US)
Pages (from-to)3849-3862
Number of pages14
JournalCommunications in Statistics - Theory and Methods
Volume20
Issue number12
DOIs
StatePublished - 1991
Externally publishedYes

Fingerprint

Block Design
Bayes
A-optimality
Sufficient Conditions
Prior Information
Robustness
Arbitrary
Experiment
Standards
Design
Family

Keywords

  • BTIB designs
  • design robustness
  • optimal designs
  • prior information
  • R-type designs

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

Bayes A-Optimal and Efficient Block Designs for Comparing Test Treatments with A Standard Treatment. / Stufken, John.

In: Communications in Statistics - Theory and Methods, Vol. 20, No. 12, 1991, p. 3849-3862.

Research output: Contribution to journalArticle

@article{d67390fdf5a8402f8c4ba9e4b0096ee0,
title = "Bayes A-Optimal and Efficient Block Designs for Comparing Test Treatments with A Standard Treatment",
abstract = "A sufficient condition for the Bayes A-optimality of block designs when comparing a standard treatment with v test treatments is given by Majumdar. (In: Optimal Design and Analysis of Experiments, Y. Dodge, V. V. Fedorov and H. P. Wynn (Eds.), 15–27, North-Holland, 1988). The priors that he considers depend on a constant a ε [0, ∞), with a - 0 corresponding to no prior information at all. The given sufficient condition, consequently, also depends on a. Large families of optimal and highly efficient designs are only known for the case a — 0. We will show how some of the results for a - 0 can be extended to obtain large families of optimal and highly efficient designs for arbitrary values of a. In addition, these results are useful when considering design robustness against an improper choice of a.",
keywords = "BTIB designs, design robustness, optimal designs, prior information, R-type designs",
author = "John Stufken",
year = "1991",
doi = "10.1080/03610929108830744",
language = "English (US)",
volume = "20",
pages = "3849--3862",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis Ltd.",
number = "12",

}

TY - JOUR

T1 - Bayes A-Optimal and Efficient Block Designs for Comparing Test Treatments with A Standard Treatment

AU - Stufken, John

PY - 1991

Y1 - 1991

N2 - A sufficient condition for the Bayes A-optimality of block designs when comparing a standard treatment with v test treatments is given by Majumdar. (In: Optimal Design and Analysis of Experiments, Y. Dodge, V. V. Fedorov and H. P. Wynn (Eds.), 15–27, North-Holland, 1988). The priors that he considers depend on a constant a ε [0, ∞), with a - 0 corresponding to no prior information at all. The given sufficient condition, consequently, also depends on a. Large families of optimal and highly efficient designs are only known for the case a — 0. We will show how some of the results for a - 0 can be extended to obtain large families of optimal and highly efficient designs for arbitrary values of a. In addition, these results are useful when considering design robustness against an improper choice of a.

AB - A sufficient condition for the Bayes A-optimality of block designs when comparing a standard treatment with v test treatments is given by Majumdar. (In: Optimal Design and Analysis of Experiments, Y. Dodge, V. V. Fedorov and H. P. Wynn (Eds.), 15–27, North-Holland, 1988). The priors that he considers depend on a constant a ε [0, ∞), with a - 0 corresponding to no prior information at all. The given sufficient condition, consequently, also depends on a. Large families of optimal and highly efficient designs are only known for the case a — 0. We will show how some of the results for a - 0 can be extended to obtain large families of optimal and highly efficient designs for arbitrary values of a. In addition, these results are useful when considering design robustness against an improper choice of a.

KW - BTIB designs

KW - design robustness

KW - optimal designs

KW - prior information

KW - R-type designs

UR - http://www.scopus.com/inward/record.url?scp=0011545920&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0011545920&partnerID=8YFLogxK

U2 - 10.1080/03610929108830744

DO - 10.1080/03610929108830744

M3 - Article

VL - 20

SP - 3849

EP - 3862

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 12

ER -