On locally optimal designs for generalized linear models with group effects

John Stufken, Min Yang

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Generalized linear models with group effects are commonly used in scientific studies. However, there appear to be no results for selecting optimal designs. In this paper, we identify the structure of locally optimal designs, provide a general strategy to determine the design points and the corresponding weights for optimal designs, and present theoretical results for the special case of D-optimality. The results can be applied to many commonly studied models, including the logistic, probit, and loglinear models. The design region can be restricted or unrestricted, and the results can also be applied for a multi-stage approach.

Original languageEnglish (US)
Pages (from-to)1765-1786
Number of pages22
JournalStatistica Sinica
Volume22
Issue number4
DOIs
StatePublished - Oct 2012
Externally publishedYes

Fingerprint

Locally Optimal Design
Generalized Linear Model
D-optimality
Probit Model
Log-linear Models
Logistic Model
Generalized linear model

Keywords

  • A-optimality
  • Binary response
  • D-optimality
  • Loewner ordering
  • Logistic model
  • Loglinear model
  • Probit model

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

On locally optimal designs for generalized linear models with group effects. / Stufken, John; Yang, Min.

In: Statistica Sinica, Vol. 22, No. 4, 10.2012, p. 1765-1786.

Research output: Contribution to journalArticle

Stufken, John ; Yang, Min. / On locally optimal designs for generalized linear models with group effects. In: Statistica Sinica. 2012 ; Vol. 22, No. 4. pp. 1765-1786.
@article{2f04dd89fd854acca2b2d6e4536c335e,
title = "On locally optimal designs for generalized linear models with group effects",
abstract = "Generalized linear models with group effects are commonly used in scientific studies. However, there appear to be no results for selecting optimal designs. In this paper, we identify the structure of locally optimal designs, provide a general strategy to determine the design points and the corresponding weights for optimal designs, and present theoretical results for the special case of D-optimality. The results can be applied to many commonly studied models, including the logistic, probit, and loglinear models. The design region can be restricted or unrestricted, and the results can also be applied for a multi-stage approach.",
keywords = "A-optimality, Binary response, D-optimality, Loewner ordering, Logistic model, Loglinear model, Probit model",
author = "John Stufken and Min Yang",
year = "2012",
month = "10",
doi = "10.5705/ss.2010.261",
language = "English (US)",
volume = "22",
pages = "1765--1786",
journal = "Statistica Sinica",
issn = "1017-0405",
publisher = "Institute of Statistical Science",
number = "4",

}

TY - JOUR

T1 - On locally optimal designs for generalized linear models with group effects

AU - Stufken, John

AU - Yang, Min

PY - 2012/10

Y1 - 2012/10

N2 - Generalized linear models with group effects are commonly used in scientific studies. However, there appear to be no results for selecting optimal designs. In this paper, we identify the structure of locally optimal designs, provide a general strategy to determine the design points and the corresponding weights for optimal designs, and present theoretical results for the special case of D-optimality. The results can be applied to many commonly studied models, including the logistic, probit, and loglinear models. The design region can be restricted or unrestricted, and the results can also be applied for a multi-stage approach.

AB - Generalized linear models with group effects are commonly used in scientific studies. However, there appear to be no results for selecting optimal designs. In this paper, we identify the structure of locally optimal designs, provide a general strategy to determine the design points and the corresponding weights for optimal designs, and present theoretical results for the special case of D-optimality. The results can be applied to many commonly studied models, including the logistic, probit, and loglinear models. The design region can be restricted or unrestricted, and the results can also be applied for a multi-stage approach.

KW - A-optimality

KW - Binary response

KW - D-optimality

KW - Loewner ordering

KW - Logistic model

KW - Loglinear model

KW - Probit model

UR - http://www.scopus.com/inward/record.url?scp=84866850234&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866850234&partnerID=8YFLogxK

U2 - 10.5705/ss.2010.261

DO - 10.5705/ss.2010.261

M3 - Article

AN - SCOPUS:84866850234

VL - 22

SP - 1765

EP - 1786

JO - Statistica Sinica

JF - Statistica Sinica

SN - 1017-0405

IS - 4

ER -