Adaptive Bayesian c-optimal design for estimating multiple EDps under the 4-paramter logistic model

Anqing Zhang, Seung Won Hyun

Research output: Contribution to journalArticle

Abstract

Under nonlinear models, optimal design truly depends on the pre-specified values of model parameter. If the nominal values of the parameter are not close to the true values, optimal designs become far from optimum. In this study, we focus on constructing an optimal design that works well for estimating multiple EDps taking into account the parameter uncertainty. To address the parameter dependency, an adaptive design technique is applied by incorporating Bayesian paradigm. One challenging task for the Bayesian approach is that it requires heavy computation when search for the Bayesian optimal design. To overcome this problem, a clustering method can be employed. We propose an adaptive Bayesian c-optimal design that works fairly well for estimating multiple values of EDp simultaneously, whilst accounting for the parameter uncertainty. We use the flexible 4-paramter logistic model to illustrate the methodology but our approach can be extended to other types of nonlinear models. We also examine the performance of our proposed design by comparing with other traditional designs through different scenarios of simulations given a wide range of mis-specified model parameters.

Original languageEnglish (US)
Pages (from-to)183-192
Number of pages10
JournalModel Assisted Statistics and Applications
Volume14
Issue number2
DOIs
StatePublished - Jan 1 2019

Fingerprint

Logistic Model
Logistics
Parameter Uncertainty
Nonlinear Model
Bayesian Optimal Design
Misspecified Model
Adaptive Design
Clustering Methods
Bayesian Approach
Categorical or nominal
Paradigm
Scenarios
Optimal design
Methodology
Range of data
Simulation
Design
Model
Uncertainty

Keywords

  • Bayesian paradigm
  • C-optimality
  • Clustering method
  • Dose-finding study
  • Parameter uncertainty
  • Target doses estimation

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation
  • Applied Mathematics

Cite this

Adaptive Bayesian c-optimal design for estimating multiple EDps under the 4-paramter logistic model. / Zhang, Anqing; Hyun, Seung Won.

In: Model Assisted Statistics and Applications, Vol. 14, No. 2, 01.01.2019, p. 183-192.

Research output: Contribution to journalArticle

@article{2710432158284668971897e92985af3f,
title = "Adaptive Bayesian c-optimal design for estimating multiple EDps under the 4-paramter logistic model",
abstract = "Under nonlinear models, optimal design truly depends on the pre-specified values of model parameter. If the nominal values of the parameter are not close to the true values, optimal designs become far from optimum. In this study, we focus on constructing an optimal design that works well for estimating multiple EDps taking into account the parameter uncertainty. To address the parameter dependency, an adaptive design technique is applied by incorporating Bayesian paradigm. One challenging task for the Bayesian approach is that it requires heavy computation when search for the Bayesian optimal design. To overcome this problem, a clustering method can be employed. We propose an adaptive Bayesian c-optimal design that works fairly well for estimating multiple values of EDp simultaneously, whilst accounting for the parameter uncertainty. We use the flexible 4-paramter logistic model to illustrate the methodology but our approach can be extended to other types of nonlinear models. We also examine the performance of our proposed design by comparing with other traditional designs through different scenarios of simulations given a wide range of mis-specified model parameters.",
keywords = "Bayesian paradigm, C-optimality, Clustering method, Dose-finding study, Parameter uncertainty, Target doses estimation",
author = "Anqing Zhang and Hyun, {Seung Won}",
year = "2019",
month = "1",
day = "1",
doi = "10.3233/MAS-190459",
language = "English (US)",
volume = "14",
pages = "183--192",
journal = "Model Assisted Statistics and Applications",
issn = "1574-1699",
publisher = "IOS Press",
number = "2",

}

TY - JOUR

T1 - Adaptive Bayesian c-optimal design for estimating multiple EDps under the 4-paramter logistic model

AU - Zhang, Anqing

AU - Hyun, Seung Won

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Under nonlinear models, optimal design truly depends on the pre-specified values of model parameter. If the nominal values of the parameter are not close to the true values, optimal designs become far from optimum. In this study, we focus on constructing an optimal design that works well for estimating multiple EDps taking into account the parameter uncertainty. To address the parameter dependency, an adaptive design technique is applied by incorporating Bayesian paradigm. One challenging task for the Bayesian approach is that it requires heavy computation when search for the Bayesian optimal design. To overcome this problem, a clustering method can be employed. We propose an adaptive Bayesian c-optimal design that works fairly well for estimating multiple values of EDp simultaneously, whilst accounting for the parameter uncertainty. We use the flexible 4-paramter logistic model to illustrate the methodology but our approach can be extended to other types of nonlinear models. We also examine the performance of our proposed design by comparing with other traditional designs through different scenarios of simulations given a wide range of mis-specified model parameters.

AB - Under nonlinear models, optimal design truly depends on the pre-specified values of model parameter. If the nominal values of the parameter are not close to the true values, optimal designs become far from optimum. In this study, we focus on constructing an optimal design that works well for estimating multiple EDps taking into account the parameter uncertainty. To address the parameter dependency, an adaptive design technique is applied by incorporating Bayesian paradigm. One challenging task for the Bayesian approach is that it requires heavy computation when search for the Bayesian optimal design. To overcome this problem, a clustering method can be employed. We propose an adaptive Bayesian c-optimal design that works fairly well for estimating multiple values of EDp simultaneously, whilst accounting for the parameter uncertainty. We use the flexible 4-paramter logistic model to illustrate the methodology but our approach can be extended to other types of nonlinear models. We also examine the performance of our proposed design by comparing with other traditional designs through different scenarios of simulations given a wide range of mis-specified model parameters.

KW - Bayesian paradigm

KW - C-optimality

KW - Clustering method

KW - Dose-finding study

KW - Parameter uncertainty

KW - Target doses estimation

UR - http://www.scopus.com/inward/record.url?scp=85066310791&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066310791&partnerID=8YFLogxK

U2 - 10.3233/MAS-190459

DO - 10.3233/MAS-190459

M3 - Article

VL - 14

SP - 183

EP - 192

JO - Model Assisted Statistics and Applications

JF - Model Assisted Statistics and Applications

SN - 1574-1699

IS - 2

ER -