Identification of the minimum effective dose for normally distributed data using a Bayesian variable selection approach

Research output: Contribution to journal › Article › Research › peer review

Authors

  • Martin Otava
  • Ziv Shkedy
  • Ludwig A. Hothorn
  • Willem Talloen
  • Daniel Gerhard
  • Adetayo Kasim

Research Organisations

External Research Organisations

  • Hasselt University
  • Johnson & Johnson
  • University of Canterbury
  • University of Durham
View graph of relations

Details

Original languageEnglish
Pages (from-to)1073-1088
Number of pages16
JournalJournal of Biopharmaceutical Statistics
Volume27
Issue number6
Early online date22 Mar 2017
Publication statusPublished - 2 Nov 2017

Abstract

The identification of the minimum effective dose is of high importance in the drug development process. In early stage screening experiments, establishing the minimum effective dose can be translated into a model selection based on information criteria. The presented alternative, Bayesian variable selection approach, allows for selection of the minimum effective dose, while taking into account model uncertainty. The performance of Bayesian variable selection is compared with the generalized order restricted information criterion on two dose-response experiments and through the simulations study. Which method has performed better depends on the complexity of the underlying model and the effect size relative to noise.

Keywords

    Bayesian variable selection, minimum effective dose, model selection, model uncertainty, order restricted models

ASJC Scopus subject areas

Cite this

Identification of the minimum effective dose for normally distributed data using a Bayesian variable selection approach. / Otava, Martin; Shkedy, Ziv; Hothorn, Ludwig A. et al.
In: Journal of Biopharmaceutical Statistics, Vol. 27, No. 6, 02.11.2017, p. 1073-1088.

Research output: Contribution to journal › Article › Research › peer review

Otava M, Shkedy Z, Hothorn LA, Talloen W, Gerhard D, Kasim A. Identification of the minimum effective dose for normally distributed data using a Bayesian variable selection approach. Journal of Biopharmaceutical Statistics. 2017 Nov 2;27(6):1073-1088. Epub 2017 Mar 22. doi: 10.1080/10543406.2017.1295247
Download
@article{31a23d8c773c4a77910b889448fddb0c,
title = "Identification of the minimum effective dose for normally distributed data using a Bayesian variable selection approach",
abstract = "The identification of the minimum effective dose is of high importance in the drug development process. In early stage screening experiments, establishing the minimum effective dose can be translated into a model selection based on information criteria. The presented alternative, Bayesian variable selection approach, allows for selection of the minimum effective dose, while taking into account model uncertainty. The performance of Bayesian variable selection is compared with the generalized order restricted information criterion on two dose-response experiments and through the simulations study. Which method has performed better depends on the complexity of the underlying model and the effect size relative to noise.",
keywords = "Bayesian variable selection, minimum effective dose, model selection, model uncertainty, order restricted models",
author = "Martin Otava and Ziv Shkedy and Hothorn, {Ludwig A.} and Willem Talloen and Daniel Gerhard and Adetayo Kasim",
note = "Funding Information: Martin Otava and Ziv Shkedy gratefully acknowledge the support from the IAP Research Network P7/06 of the Belgian State (Belgian Science Policy). Martin Otava gratefully acknowledge the financial support of the Research Project BOF11DOC09 of Hasselt University. The computational resources and services used in this work were provided by the VSC (Flemish Supercomputer Center), funded by the Hercules Foundation and the Flemish Government, department EWI. Martin Otava and Ziv Shkedy gratefully acknowledge the support from the IAP Research Network P7/06 of the Belgian State (Belgian Science Policy). Martin Otava gratefully acknowledge the financial support of the Research Project BOF11DOC09 of Hasselt University. ",
year = "2017",
month = nov,
day = "2",
doi = "10.1080/10543406.2017.1295247",
language = "English",
volume = "27",
pages = "1073--1088",
journal = "Journal of Biopharmaceutical Statistics",
issn = "1054-3406",
publisher = "Taylor and Francis Ltd.",
number = "6",

}

Download

TY - JOUR

T1 - Identification of the minimum effective dose for normally distributed data using a Bayesian variable selection approach

AU - Otava, Martin

AU - Shkedy, Ziv

AU - Hothorn, Ludwig A.

AU - Talloen, Willem

AU - Gerhard, Daniel

AU - Kasim, Adetayo

N1 - Funding Information: Martin Otava and Ziv Shkedy gratefully acknowledge the support from the IAP Research Network P7/06 of the Belgian State (Belgian Science Policy). Martin Otava gratefully acknowledge the financial support of the Research Project BOF11DOC09 of Hasselt University. The computational resources and services used in this work were provided by the VSC (Flemish Supercomputer Center), funded by the Hercules Foundation and the Flemish Government, department EWI. Martin Otava and Ziv Shkedy gratefully acknowledge the support from the IAP Research Network P7/06 of the Belgian State (Belgian Science Policy). Martin Otava gratefully acknowledge the financial support of the Research Project BOF11DOC09 of Hasselt University.

PY - 2017/11/2

Y1 - 2017/11/2

N2 - The identification of the minimum effective dose is of high importance in the drug development process. In early stage screening experiments, establishing the minimum effective dose can be translated into a model selection based on information criteria. The presented alternative, Bayesian variable selection approach, allows for selection of the minimum effective dose, while taking into account model uncertainty. The performance of Bayesian variable selection is compared with the generalized order restricted information criterion on two dose-response experiments and through the simulations study. Which method has performed better depends on the complexity of the underlying model and the effect size relative to noise.

AB - The identification of the minimum effective dose is of high importance in the drug development process. In early stage screening experiments, establishing the minimum effective dose can be translated into a model selection based on information criteria. The presented alternative, Bayesian variable selection approach, allows for selection of the minimum effective dose, while taking into account model uncertainty. The performance of Bayesian variable selection is compared with the generalized order restricted information criterion on two dose-response experiments and through the simulations study. Which method has performed better depends on the complexity of the underlying model and the effect size relative to noise.

KW - Bayesian variable selection

KW - minimum effective dose

KW - model selection

KW - model uncertainty

KW - order restricted models

UR - http://www.scopus.com/inward/record.url?scp=85015864653&partnerID=8YFLogxK

U2 - 10.1080/10543406.2017.1295247

DO - 10.1080/10543406.2017.1295247

M3 - Article

C2 - 28328286

AN - SCOPUS:85015864653

VL - 27

SP - 1073

EP - 1088

JO - Journal of Biopharmaceutical Statistics

JF - Journal of Biopharmaceutical Statistics

SN - 1054-3406

IS - 6

ER -