Optimal designs for binary response models with multiple nonnegative variables

Shih Hao Huang; Mong Na Lo Huang; Cheng Wei Lin

doi:10.1016/j.jspi.2019.09.006

Optimal designs for binary response models with multiple nonnegative variables

Shih Hao Huang, Mong Na Lo Huang, Cheng Wei Lin

Department of Mathematics

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

1 Scopus citations

Abstract

In this work we investigate locally optimal designs for binary response models with multiple nonnegative explanatory variables. We characterize an essentially complete class with respect to Schur ordering, in which a scaled ϕ_p-optimal design exists for any given p∈[−∞,1]. In particular, we explicitly identify D-optimal designs for logit, probit, double exponential, double reciprocal models within the class.

Original language	English
Pages (from-to)	75-83
Number of pages	9
Journal	Journal of Statistical Planning and Inference
Volume	206
DOIs	https://doi.org/10.1016/j.jspi.2019.09.006
State	Published - May 2020

Keywords

D-optimality
Essentially complete class
Scaled ϕ-optimality
Schur ordering

Access to Document

10.1016/j.jspi.2019.09.006

Informative Canonical Correlation Analysis with Applications to Image Data(2/2)
Huang, S.-H. (PI)
1/08/19 → 31/10/20
Project: Research

Cite this

@article{eef319282fca4f86a7f427cfeb286649,

title = "Optimal designs for binary response models with multiple nonnegative variables",

abstract = "In this work we investigate locally optimal designs for binary response models with multiple nonnegative explanatory variables. We characterize an essentially complete class with respect to Schur ordering, in which a scaled ϕp-optimal design exists for any given p∈[−∞,1]. In particular, we explicitly identify D-optimal designs for logit, probit, double exponential, double reciprocal models within the class.",

keywords = "D-optimality, Essentially complete class, Scaled ϕ-optimality, Schur ordering",

author = "Huang, {Shih Hao} and {Lo Huang}, {Mong Na} and Lin, {Cheng Wei}",

note = "Publisher Copyright: {\textcopyright} 2019 Elsevier B.V.",

year = "2020",

month = may,

doi = "10.1016/j.jspi.2019.09.006",

language = "???core.languages.en_GB???",

volume = "206",

pages = "75--83",

journal = "Journal of Statistical Planning and Inference",

issn = "0378-3758",

}

TY - JOUR

T1 - Optimal designs for binary response models with multiple nonnegative variables

AU - Huang, Shih Hao

AU - Lo Huang, Mong Na

AU - Lin, Cheng Wei

PY - 2020/5

Y1 - 2020/5

N2 - In this work we investigate locally optimal designs for binary response models with multiple nonnegative explanatory variables. We characterize an essentially complete class with respect to Schur ordering, in which a scaled ϕp-optimal design exists for any given p∈[−∞,1]. In particular, we explicitly identify D-optimal designs for logit, probit, double exponential, double reciprocal models within the class.

AB - In this work we investigate locally optimal designs for binary response models with multiple nonnegative explanatory variables. We characterize an essentially complete class with respect to Schur ordering, in which a scaled ϕp-optimal design exists for any given p∈[−∞,1]. In particular, we explicitly identify D-optimal designs for logit, probit, double exponential, double reciprocal models within the class.

KW - D-optimality

KW - Essentially complete class

KW - Scaled ϕ-optimality

KW - Schur ordering

UR - http://www.scopus.com/inward/record.url?scp=85072838034&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2019.09.006

DO - 10.1016/j.jspi.2019.09.006

M3 - 期刊論文

AN - SCOPUS:85072838034

SN - 0378-3758

VL - 206

SP - 75

EP - 83

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

ER -

Optimal designs for binary response models with multiple nonnegative variables

Abstract

Keywords

Access to Document

Fingerprint

Projects

Informative Canonical Correlation Analysis with Applications to Image Data(2/2)

Cite this