A Score Test for Testing a Marginalized Zero-Inflated Poisson Regression Model Against a Marginalized Zero-Inflated Negative Binomial Regression Model

Gul Inan; John Preisser; Kalyan Das

doi:10.1007/s13253-017-0314-5

A Score Test for Testing a Marginalized Zero-Inflated Poisson Regression Model Against a Marginalized Zero-Inflated Negative Binomial Regression Model

Gul Inan^*, John Preisser, Kalyan Das

^*Corresponding author for this work

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

5 Citations (Scopus)

Abstract

Marginalized zero-inflated count regression models (Long et al. in Stat Med 33(29):5151–5165, 2014) provide direct inference on overall exposure effects. Unlike standard zero-inflated models, marginalized models specify a regression model component for the marginal mean in addition to a component for the probability of an excess zero. This study proposes a score test for testing a marginalized zero-inflated Poisson model against a marginalized zero-inflated negative binomial model for model selection based on an assessment of over-dispersion. The sampling distribution and empirical power of the proposed score test are investigated via a Monte Carlo simulation study, and the procedure is illustrated with data from a horticultural experiment. Supplementary materials accompanying this paper appear on-line.

Original language	English
Pages (from-to)	113-128
Number of pages	16
Journal	Journal of Agricultural, Biological, and Environmental Statistics
Volume	23
Issue number	1
DOIs	https://doi.org/10.1007/s13253-017-0314-5
Publication status	Published - 1 Mar 2018
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2017, International Biometric Society.

Funding

Part of this study was carried out, while Gul Inan was visiting Department of Biostatistics, University of North Carolina—Chapel Hill, USA. She would like to thank the Scientific and Technological Research Council of Turkey (TUBITAK) for funding her postdoctoral studies in USA. This study was supported by the International Biometric Society and Institute of Mathematical Statistics travel grant programmes to be presented at 9th Conference of the Eastern Mediterranean Region of the International Biometric Society and Joint Statistical Meetings, respectively, in 2017.

Funders	Funder number
Eastern Mediterranean Region of the International Biometric Society
Institute of Mathematical Statistics
TUBITAK
International Biometric Society
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu

Keywords

Count data
Excess zeros
Marginal models
Over-dispersion
Score test

Access to Document

10.1007/s13253-017-0314-5

Cite this

@article{1effa7f8519941e88aa55f9e0bc10c57,

title = "A Score Test for Testing a Marginalized Zero-Inflated Poisson Regression Model Against a Marginalized Zero-Inflated Negative Binomial Regression Model",

abstract = "Marginalized zero-inflated count regression models (Long et al. in Stat Med 33(29):5151–5165, 2014) provide direct inference on overall exposure effects. Unlike standard zero-inflated models, marginalized models specify a regression model component for the marginal mean in addition to a component for the probability of an excess zero. This study proposes a score test for testing a marginalized zero-inflated Poisson model against a marginalized zero-inflated negative binomial model for model selection based on an assessment of over-dispersion. The sampling distribution and empirical power of the proposed score test are investigated via a Monte Carlo simulation study, and the procedure is illustrated with data from a horticultural experiment. Supplementary materials accompanying this paper appear on-line.",

keywords = "Count data, Excess zeros, Marginal models, Over-dispersion, Score test",

author = "Gul Inan and John Preisser and Kalyan Das",

note = "Publisher Copyright: {\textcopyright} 2017, International Biometric Society.",

year = "2018",

month = mar,

day = "1",

doi = "10.1007/s13253-017-0314-5",

language = "English",

volume = "23",

pages = "113--128",

journal = "Journal of Agricultural, Biological, and Environmental Statistics",

issn = "1085-7117",

publisher = "Springer",

number = "1",

}

A Score Test for Testing a Marginalized Zero-Inflated Poisson Regression Model Against a Marginalized Zero-Inflated Negative Binomial Regression Model. / Inan, Gul; Preisser, John; Das, Kalyan.
In: Journal of Agricultural, Biological, and Environmental Statistics, Vol. 23, No. 1, 01.03.2018, p. 113-128.

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

TY - JOUR

T1 - A Score Test for Testing a Marginalized Zero-Inflated Poisson Regression Model Against a Marginalized Zero-Inflated Negative Binomial Regression Model

AU - Inan, Gul

AU - Preisser, John

AU - Das, Kalyan

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Marginalized zero-inflated count regression models (Long et al. in Stat Med 33(29):5151–5165, 2014) provide direct inference on overall exposure effects. Unlike standard zero-inflated models, marginalized models specify a regression model component for the marginal mean in addition to a component for the probability of an excess zero. This study proposes a score test for testing a marginalized zero-inflated Poisson model against a marginalized zero-inflated negative binomial model for model selection based on an assessment of over-dispersion. The sampling distribution and empirical power of the proposed score test are investigated via a Monte Carlo simulation study, and the procedure is illustrated with data from a horticultural experiment. Supplementary materials accompanying this paper appear on-line.

AB - Marginalized zero-inflated count regression models (Long et al. in Stat Med 33(29):5151–5165, 2014) provide direct inference on overall exposure effects. Unlike standard zero-inflated models, marginalized models specify a regression model component for the marginal mean in addition to a component for the probability of an excess zero. This study proposes a score test for testing a marginalized zero-inflated Poisson model against a marginalized zero-inflated negative binomial model for model selection based on an assessment of over-dispersion. The sampling distribution and empirical power of the proposed score test are investigated via a Monte Carlo simulation study, and the procedure is illustrated with data from a horticultural experiment. Supplementary materials accompanying this paper appear on-line.

KW - Count data

KW - Excess zeros

KW - Marginal models

KW - Over-dispersion

KW - Score test

UR - http://www.scopus.com/inward/record.url?scp=85034646033&partnerID=8YFLogxK

U2 - 10.1007/s13253-017-0314-5

DO - 10.1007/s13253-017-0314-5

M3 - Article

AN - SCOPUS:85034646033

SN - 1085-7117

VL - 23

SP - 113

EP - 128

JO - Journal of Agricultural, Biological, and Environmental Statistics

JF - Journal of Agricultural, Biological, and Environmental Statistics

IS - 1

ER -

A Score Test for Testing a Marginalized Zero-Inflated Poisson Regression Model Against a Marginalized Zero-Inflated Negative Binomial Regression Model

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this