Parametric empirical Bayes estimation for a class of extended log-linear regression models

Wanzhu Tu, Walter W. Piegorsch

Research output: Contribution to journalArticle

Abstract

This paper presents a fully parametric empirical Bayes approach for the analysis of count data, with emphasis on its application to environmental toxicity data. A hierarchical structure for the mean response is developed from a generalized linear model, based on a Poisson distribution. The linear predictor is embedded at the prior level of the hierarchy. This allows for enhanced flexibility when accounting for extra-Poisson variation, which is often displayed with count data from environmental bioassays. The model expands upon the traditional log-linear model in two different ways: (1) it extends the Poisson distributional assumption; and (2) it incorporates an extended family of link functions that includes the log link as a special case. The main advantage of this approach is that it combines relative computational simplicity with hierarchical modeling flexibility. In this paper, we emphasize the model's development and the practical issues related to the analysis. We describe an application of the proposed model to data from an environmental mutagenesis experiment. Copyright (C) 2000 John Wiley and Sons, Ltd.

Original languageEnglish
Pages (from-to)271-285
Number of pages15
JournalEnvironmetrics
Volume11
Issue number3
DOIs
StatePublished - May 2000

Fingerprint

Empirical Bayes Estimation
Log-linear Models
Linear Regression Model
Linear regression
Count Data
Siméon Denis Poisson
Flexibility
Hierarchical Modeling
Link Function
Bioassay
Empirical Bayes
Poisson distribution
Generalized Linear Model
Toxicity
Hierarchical Structure
Expand
Predictors
Simplicity
Mutagenesis
Model

Keywords

  • Count data
  • Extra-Poisson variability
  • Hierarchical model
  • Maximum likelihood
  • Parametric empirical Bayes analysis

ASJC Scopus subject areas

  • Environmental Science(all)
  • Environmental Chemistry
  • Statistics and Probability

Cite this

Parametric empirical Bayes estimation for a class of extended log-linear regression models. / Tu, Wanzhu; Piegorsch, Walter W.

In: Environmetrics, Vol. 11, No. 3, 05.2000, p. 271-285.

Research output: Contribution to journalArticle

@article{cce01a784aea488ca39d2598cd6108e8,
title = "Parametric empirical Bayes estimation for a class of extended log-linear regression models",
abstract = "This paper presents a fully parametric empirical Bayes approach for the analysis of count data, with emphasis on its application to environmental toxicity data. A hierarchical structure for the mean response is developed from a generalized linear model, based on a Poisson distribution. The linear predictor is embedded at the prior level of the hierarchy. This allows for enhanced flexibility when accounting for extra-Poisson variation, which is often displayed with count data from environmental bioassays. The model expands upon the traditional log-linear model in two different ways: (1) it extends the Poisson distributional assumption; and (2) it incorporates an extended family of link functions that includes the log link as a special case. The main advantage of this approach is that it combines relative computational simplicity with hierarchical modeling flexibility. In this paper, we emphasize the model's development and the practical issues related to the analysis. We describe an application of the proposed model to data from an environmental mutagenesis experiment. Copyright (C) 2000 John Wiley and Sons, Ltd.",
keywords = "Count data, Extra-Poisson variability, Hierarchical model, Maximum likelihood, Parametric empirical Bayes analysis",
author = "Wanzhu Tu and Piegorsch, {Walter W.}",
year = "2000",
month = "5",
doi = "10.1002/(SICI)1099-095X(200005/06)11:3<271::AID-ENV407>3.0.CO;2-T",
language = "English",
volume = "11",
pages = "271--285",
journal = "Environmetrics",
issn = "1180-4009",
publisher = "John Wiley and Sons Ltd",
number = "3",

}

TY - JOUR

T1 - Parametric empirical Bayes estimation for a class of extended log-linear regression models

AU - Tu, Wanzhu

AU - Piegorsch, Walter W.

PY - 2000/5

Y1 - 2000/5

N2 - This paper presents a fully parametric empirical Bayes approach for the analysis of count data, with emphasis on its application to environmental toxicity data. A hierarchical structure for the mean response is developed from a generalized linear model, based on a Poisson distribution. The linear predictor is embedded at the prior level of the hierarchy. This allows for enhanced flexibility when accounting for extra-Poisson variation, which is often displayed with count data from environmental bioassays. The model expands upon the traditional log-linear model in two different ways: (1) it extends the Poisson distributional assumption; and (2) it incorporates an extended family of link functions that includes the log link as a special case. The main advantage of this approach is that it combines relative computational simplicity with hierarchical modeling flexibility. In this paper, we emphasize the model's development and the practical issues related to the analysis. We describe an application of the proposed model to data from an environmental mutagenesis experiment. Copyright (C) 2000 John Wiley and Sons, Ltd.

AB - This paper presents a fully parametric empirical Bayes approach for the analysis of count data, with emphasis on its application to environmental toxicity data. A hierarchical structure for the mean response is developed from a generalized linear model, based on a Poisson distribution. The linear predictor is embedded at the prior level of the hierarchy. This allows for enhanced flexibility when accounting for extra-Poisson variation, which is often displayed with count data from environmental bioassays. The model expands upon the traditional log-linear model in two different ways: (1) it extends the Poisson distributional assumption; and (2) it incorporates an extended family of link functions that includes the log link as a special case. The main advantage of this approach is that it combines relative computational simplicity with hierarchical modeling flexibility. In this paper, we emphasize the model's development and the practical issues related to the analysis. We describe an application of the proposed model to data from an environmental mutagenesis experiment. Copyright (C) 2000 John Wiley and Sons, Ltd.

KW - Count data

KW - Extra-Poisson variability

KW - Hierarchical model

KW - Maximum likelihood

KW - Parametric empirical Bayes analysis

UR - http://www.scopus.com/inward/record.url?scp=0034118605&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034118605&partnerID=8YFLogxK

U2 - 10.1002/(SICI)1099-095X(200005/06)11:3<271::AID-ENV407>3.0.CO;2-T

DO - 10.1002/(SICI)1099-095X(200005/06)11:3<271::AID-ENV407>3.0.CO;2-T

M3 - Article

AN - SCOPUS:0034118605

VL - 11

SP - 271

EP - 285

JO - Environmetrics

JF - Environmetrics

SN - 1180-4009

IS - 3

ER -