Optimal designs for response functions with a downturn

Seung Won Hyun, Min Yang, Nancy Flournoy

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In many toxicological assays, interactions between primary and secondary effects may cause a downturn in mean responses at high doses. In this situation, the typical monotonicity assumption is invalid and may be quite misleading. Prior literature addresses the analysis of response functions with a downturn, but so far as we know, this paper initiates the study of experimental design for this situation. A growth model is combined with a death model to allow for the downturn in mean doses. Several different objective functions are studied. When the number of treatments equals the number of parameters, Fisher information is found to be independent of the model of the treatment means and on the magnitudes of the treatments. In general, A- and DA-optimal weights for estimating adjacent mean differences are found analytically for a simple model and numerically for a biologically motivated model. Results on c-optimality are also obtained for estimating the peak dose and the EC50 (the treatment with response half way between the control and the peak response on the increasing portion of the response function). Finally, when interest lies only in the increasing portion of the response function, we propose composite D-optimal designs.

Original languageEnglish (US)
Pages (from-to)559-575
Number of pages17
JournalJournal of Statistical Planning and Inference
Volume141
Issue number1
DOIs
StatePublished - Jan 1 2011

Fingerprint

Response Function
Dose
C-optimality
D-optimal Design
Fisher Information
Growth Model
Experimental design
Model
Monotonicity
Adjacent
Objective function
Design of experiments
Composite
Assays
Optimal design
Interaction
Composite materials

Keywords

  • A-optimality
  • D-optimality
  • D-optimality
  • Dose-response
  • EC
  • Endocrine-disrupting chemicals
  • Experimental design
  • Laboratory studies
  • Nonlinear response function
  • Optimal weights
  • Peak dose
  • Successive mean differences
  • Toxicological assays

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Cite this

Optimal designs for response functions with a downturn. / Hyun, Seung Won; Yang, Min; Flournoy, Nancy.

In: Journal of Statistical Planning and Inference, Vol. 141, No. 1, 01.01.2011, p. 559-575.

Research output: Contribution to journalArticle

Hyun, Seung Won ; Yang, Min ; Flournoy, Nancy. / Optimal designs for response functions with a downturn. In: Journal of Statistical Planning and Inference. 2011 ; Vol. 141, No. 1. pp. 559-575.
@article{3a209e53ac954eb98a0aa25fe92334c6,
title = "Optimal designs for response functions with a downturn",
abstract = "In many toxicological assays, interactions between primary and secondary effects may cause a downturn in mean responses at high doses. In this situation, the typical monotonicity assumption is invalid and may be quite misleading. Prior literature addresses the analysis of response functions with a downturn, but so far as we know, this paper initiates the study of experimental design for this situation. A growth model is combined with a death model to allow for the downturn in mean doses. Several different objective functions are studied. When the number of treatments equals the number of parameters, Fisher information is found to be independent of the model of the treatment means and on the magnitudes of the treatments. In general, A- and DA-optimal weights for estimating adjacent mean differences are found analytically for a simple model and numerically for a biologically motivated model. Results on c-optimality are also obtained for estimating the peak dose and the EC50 (the treatment with response half way between the control and the peak response on the increasing portion of the response function). Finally, when interest lies only in the increasing portion of the response function, we propose composite D-optimal designs.",
keywords = "A-optimality, D-optimality, D-optimality, Dose-response, EC, Endocrine-disrupting chemicals, Experimental design, Laboratory studies, Nonlinear response function, Optimal weights, Peak dose, Successive mean differences, Toxicological assays",
author = "Hyun, {Seung Won} and Min Yang and Nancy Flournoy",
year = "2011",
month = "1",
day = "1",
doi = "10.1016/j.jspi.2010.07.003",
language = "English (US)",
volume = "141",
pages = "559--575",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Optimal designs for response functions with a downturn

AU - Hyun, Seung Won

AU - Yang, Min

AU - Flournoy, Nancy

PY - 2011/1/1

Y1 - 2011/1/1

N2 - In many toxicological assays, interactions between primary and secondary effects may cause a downturn in mean responses at high doses. In this situation, the typical monotonicity assumption is invalid and may be quite misleading. Prior literature addresses the analysis of response functions with a downturn, but so far as we know, this paper initiates the study of experimental design for this situation. A growth model is combined with a death model to allow for the downturn in mean doses. Several different objective functions are studied. When the number of treatments equals the number of parameters, Fisher information is found to be independent of the model of the treatment means and on the magnitudes of the treatments. In general, A- and DA-optimal weights for estimating adjacent mean differences are found analytically for a simple model and numerically for a biologically motivated model. Results on c-optimality are also obtained for estimating the peak dose and the EC50 (the treatment with response half way between the control and the peak response on the increasing portion of the response function). Finally, when interest lies only in the increasing portion of the response function, we propose composite D-optimal designs.

AB - In many toxicological assays, interactions between primary and secondary effects may cause a downturn in mean responses at high doses. In this situation, the typical monotonicity assumption is invalid and may be quite misleading. Prior literature addresses the analysis of response functions with a downturn, but so far as we know, this paper initiates the study of experimental design for this situation. A growth model is combined with a death model to allow for the downturn in mean doses. Several different objective functions are studied. When the number of treatments equals the number of parameters, Fisher information is found to be independent of the model of the treatment means and on the magnitudes of the treatments. In general, A- and DA-optimal weights for estimating adjacent mean differences are found analytically for a simple model and numerically for a biologically motivated model. Results on c-optimality are also obtained for estimating the peak dose and the EC50 (the treatment with response half way between the control and the peak response on the increasing portion of the response function). Finally, when interest lies only in the increasing portion of the response function, we propose composite D-optimal designs.

KW - A-optimality

KW - D-optimality

KW - D-optimality

KW - Dose-response

KW - EC

KW - Endocrine-disrupting chemicals

KW - Experimental design

KW - Laboratory studies

KW - Nonlinear response function

KW - Optimal weights

KW - Peak dose

KW - Successive mean differences

KW - Toxicological assays

UR - http://www.scopus.com/inward/record.url?scp=77956284216&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956284216&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2010.07.003

DO - 10.1016/j.jspi.2010.07.003

M3 - Article

AN - SCOPUS:77956284216

VL - 141

SP - 559

EP - 575

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

IS - 1

ER -