Support points of locally optimal designs for nonlinear models with two parameters

Min Yang, John Stufken

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

We propose a new approach for identifying the support points of a locally optimal design when the model is a nonlinear model. In contrast to the commonly used geometric approach, we use an approach based on algebraic tools. Considerations are restricted to models with two parameters, and the general results are applied to often used special cases, including logistic, probit, double exponential and double reciprocal models for binary data, a loglinear Poisson regression model for count data, and the Michaelis-Menten model. The approach, which is also of value for multi-stage experiments, works both with constrained and unconstrained design regions and is relatively easy to implement.

Original languageEnglish (US)
Pages (from-to)518-541
Number of pages24
JournalAnnals of Statistics
Volume37
Issue number1
DOIs
StatePublished - Feb 2009
Externally publishedYes

Fingerprint

Locally Optimal Design
Support Point
Nonlinear Model
Two Parameters
Probit
Poisson Regression
Count Data
Binary Data
Geometric Approach
Poisson Model
Model
Logistics
Regression Model
Experiment

Keywords

  • Binary response
  • Count data
  • Design of experiments
  • Generalized linear model
  • Loewner order
  • Michaelis-menten model
  • Multi-stage experiment
  • Optimality
  • Poisson model

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Support points of locally optimal designs for nonlinear models with two parameters. / Yang, Min; Stufken, John.

In: Annals of Statistics, Vol. 37, No. 1, 02.2009, p. 518-541.

Research output: Contribution to journalArticle

Yang, Min ; Stufken, John. / Support points of locally optimal designs for nonlinear models with two parameters. In: Annals of Statistics. 2009 ; Vol. 37, No. 1. pp. 518-541.
@article{4e09dce5326c47009821fe0a12906399,
title = "Support points of locally optimal designs for nonlinear models with two parameters",
abstract = "We propose a new approach for identifying the support points of a locally optimal design when the model is a nonlinear model. In contrast to the commonly used geometric approach, we use an approach based on algebraic tools. Considerations are restricted to models with two parameters, and the general results are applied to often used special cases, including logistic, probit, double exponential and double reciprocal models for binary data, a loglinear Poisson regression model for count data, and the Michaelis-Menten model. The approach, which is also of value for multi-stage experiments, works both with constrained and unconstrained design regions and is relatively easy to implement.",
keywords = "Binary response, Count data, Design of experiments, Generalized linear model, Loewner order, Michaelis-menten model, Multi-stage experiment, Optimality, Poisson model",
author = "Min Yang and John Stufken",
year = "2009",
month = "2",
doi = "10.1214/07-AOS560",
language = "English (US)",
volume = "37",
pages = "518--541",
journal = "Annals of Statistics",
issn = "0090-5364",
publisher = "Institute of Mathematical Statistics",
number = "1",

}

TY - JOUR

T1 - Support points of locally optimal designs for nonlinear models with two parameters

AU - Yang, Min

AU - Stufken, John

PY - 2009/2

Y1 - 2009/2

N2 - We propose a new approach for identifying the support points of a locally optimal design when the model is a nonlinear model. In contrast to the commonly used geometric approach, we use an approach based on algebraic tools. Considerations are restricted to models with two parameters, and the general results are applied to often used special cases, including logistic, probit, double exponential and double reciprocal models for binary data, a loglinear Poisson regression model for count data, and the Michaelis-Menten model. The approach, which is also of value for multi-stage experiments, works both with constrained and unconstrained design regions and is relatively easy to implement.

AB - We propose a new approach for identifying the support points of a locally optimal design when the model is a nonlinear model. In contrast to the commonly used geometric approach, we use an approach based on algebraic tools. Considerations are restricted to models with two parameters, and the general results are applied to often used special cases, including logistic, probit, double exponential and double reciprocal models for binary data, a loglinear Poisson regression model for count data, and the Michaelis-Menten model. The approach, which is also of value for multi-stage experiments, works both with constrained and unconstrained design regions and is relatively easy to implement.

KW - Binary response

KW - Count data

KW - Design of experiments

KW - Generalized linear model

KW - Loewner order

KW - Michaelis-menten model

KW - Multi-stage experiment

KW - Optimality

KW - Poisson model

UR - http://www.scopus.com/inward/record.url?scp=65349115907&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=65349115907&partnerID=8YFLogxK

U2 - 10.1214/07-AOS560

DO - 10.1214/07-AOS560

M3 - Article

VL - 37

SP - 518

EP - 541

JO - Annals of Statistics

JF - Annals of Statistics

SN - 0090-5364

IS - 1

ER -