Binary data regression: Weibull distribution

Renault Caron; Adriano Polpo

doi:10.1063/1.3275613

Binary data regression: Weibull distribution

Renault Caron, Adriano Polpo

Mathematics and Statistics

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

4 Citations (Scopus)

Abstract

The problem of estimation in binary response data has receivied a great number of alternative statistical solutions. Generalized linear models allow for a wide range of statistical models for regression data. The most used model is the logistic regression, see Hosmer et al. [6]. However, as Chen et al. [5] mentions, when the probability of a given binary response approaches 0 at a different rate than it approaches I, symmetric linkages are inappropriate. A class of models based on Weibull distribution indexed by three parameters is introduced here. Maximum likelihood methods are employed to estimate the parameters. The objective of the present paper is to show a solution for the estimation problem under the Weibull model. An example showing the quality of the model is illustrated by comparing it with the alternative probit and logit models.

Original language	English
Title of host publication	BAYESIAN INFERENCE AND MAXIMUM ENTROPY METHODS IN SCIENCE AND ENGINEERING
Editors	PM Goggans, CY Chan
Publisher	American Institute of Physics
Pages	187-193
Number of pages	7
ISBN (Print)	978-0-7354-0729-9
DOIs	https://doi.org/10.1063/1.3275613
Publication status	Published - 2009
Event	29th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering - Oxford, United States Duration: 5 Jul 2009 → 10 Jul 2009 http://inspirehep.net/record/980193

Publication series

Name	AIP Conference Proceedings
Publisher	AMER INST PHYSICS
Volume	1193
ISSN (Print)	0094-243X

Conference

Conference	29th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering
Abbreviated title	MaxEnt 2009
Country/Territory	United States
City	Oxford
Period	5/07/09 → 10/07/09
Internet address	http://inspirehep.net/record/980193

Access to Document

10.1063/1.3275613

Cite this

@inproceedings{3ee0a6fd388941a49350039e39fffe9d,

title = "Binary data regression: Weibull distribution",

abstract = "The problem of estimation in binary response data has receivied a great number of alternative statistical solutions. Generalized linear models allow for a wide range of statistical models for regression data. The most used model is the logistic regression, see Hosmer et al. [6]. However, as Chen et al. [5] mentions, when the probability of a given binary response approaches 0 at a different rate than it approaches I, symmetric linkages are inappropriate. A class of models based on Weibull distribution indexed by three parameters is introduced here. Maximum likelihood methods are employed to estimate the parameters. The objective of the present paper is to show a solution for the estimation problem under the Weibull model. An example showing the quality of the model is illustrated by comparing it with the alternative probit and logit models.",

keywords = "Weibull distribution, binary data",

author = "Renault Caron and Adriano Polpo",

year = "2009",

doi = "10.1063/1.3275613",

language = "English",

isbn = "978-0-7354-0729-9",

series = "AIP Conference Proceedings",

publisher = "American Institute of Physics",

pages = "187--193",

editor = "PM Goggans and CY Chan",

booktitle = "BAYESIAN INFERENCE AND MAXIMUM ENTROPY METHODS IN SCIENCE AND ENGINEERING",

address = "United States",

note = "29th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering, MaxEnt 2009 ; Conference date: 05-07-2009 Through 10-07-2009",

url = "http://inspirehep.net/record/980193",

}

Caron, R & Polpo, A 2009, Binary data regression: Weibull distribution. in PM Goggans & CY Chan (eds), BAYESIAN INFERENCE AND MAXIMUM ENTROPY METHODS IN SCIENCE AND ENGINEERING. AIP Conference Proceedings, vol. 1193, American Institute of Physics, pp. 187-193, 29th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering, Oxford, Mississippi, United States, 5/07/09. https://doi.org/10.1063/1.3275613

TY - GEN

T1 - Binary data regression

T2 - 29th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering

AU - Caron, Renault

AU - Polpo, Adriano

PY - 2009

Y1 - 2009

N2 - The problem of estimation in binary response data has receivied a great number of alternative statistical solutions. Generalized linear models allow for a wide range of statistical models for regression data. The most used model is the logistic regression, see Hosmer et al. [6]. However, as Chen et al. [5] mentions, when the probability of a given binary response approaches 0 at a different rate than it approaches I, symmetric linkages are inappropriate. A class of models based on Weibull distribution indexed by three parameters is introduced here. Maximum likelihood methods are employed to estimate the parameters. The objective of the present paper is to show a solution for the estimation problem under the Weibull model. An example showing the quality of the model is illustrated by comparing it with the alternative probit and logit models.

AB - The problem of estimation in binary response data has receivied a great number of alternative statistical solutions. Generalized linear models allow for a wide range of statistical models for regression data. The most used model is the logistic regression, see Hosmer et al. [6]. However, as Chen et al. [5] mentions, when the probability of a given binary response approaches 0 at a different rate than it approaches I, symmetric linkages are inappropriate. A class of models based on Weibull distribution indexed by three parameters is introduced here. Maximum likelihood methods are employed to estimate the parameters. The objective of the present paper is to show a solution for the estimation problem under the Weibull model. An example showing the quality of the model is illustrated by comparing it with the alternative probit and logit models.

KW - Weibull distribution

KW - binary data

U2 - 10.1063/1.3275613

DO - 10.1063/1.3275613

M3 - Conference paper

SN - 978-0-7354-0729-9

T3 - AIP Conference Proceedings

SP - 187

EP - 193

BT - BAYESIAN INFERENCE AND MAXIMUM ENTROPY METHODS IN SCIENCE AND ENGINEERING

A2 - Goggans, PM

A2 - Chan, CY

PB - American Institute of Physics

Y2 - 5 July 2009 through 10 July 2009

ER -

Binary data regression: Weibull distribution

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this