A score test for testing a zero-inflated Poisson regression model against zero-inflated negative binomial alternatives

Martin Ridout; John Hinde; Clarice G.B. DeméAtrio

doi:10.1111/j.0006-341X.2001.00219.x

A score test for testing a zero-inflated Poisson regression model against zero-inflated negative binomial alternatives

Martin Ridout
, John Hinde
, Clarice G.B. DeméAtrio

Horticulture Research International
University of Kent
University of Exeter
University of São Paulo

Research output: Contribution to a Journal (Peer & Non Peer) › Article › peer-review

321 Citations (Scopus)

Abstract

Count data often show a higher incidence of zero counts than would be expected if the data were Poisson distributed. Zero-inflated Poisson regression models are a useful class of models for such data, but parameter estimates may be seriously biased if the nonzero counts are overdispersed in relation to the Poisson distribution. We therefore provide a score test for testing zero-inflated Poisson regression models against zero-inflated negative binomial alternatives.

Original language	English
Pages (from-to)	219-223
Number of pages	5
Journal	Biometrics
Volume	57
Issue number	1
DOIs	https://doi.org/10.1111/j.0006-341X.2001.00219.x
Publication status	Published - 2001
Externally published	Yes

Keywords

Count data
Negative binomial
Regression model
Score test
Zero inflation

Access to Document

10.1111/j.0006-341X.2001.00219.x

Cite this

@article{ac72a0ba6ef24588a76224cb1d0f0530,

title = "A score test for testing a zero-inflated Poisson regression model against zero-inflated negative binomial alternatives",

abstract = "Count data often show a higher incidence of zero counts than would be expected if the data were Poisson distributed. Zero-inflated Poisson regression models are a useful class of models for such data, but parameter estimates may be seriously biased if the nonzero counts are overdispersed in relation to the Poisson distribution. We therefore provide a score test for testing zero-inflated Poisson regression models against zero-inflated negative binomial alternatives.",

keywords = "Count data, Negative binomial, Regression model, Score test, Zero inflation",

author = "Martin Ridout and John Hinde and Dem{\'e}Atrio, \{Clarice G.B.\}",

year = "2001",

doi = "10.1111/j.0006-341X.2001.00219.x",

language = "English",

volume = "57",

pages = "219--223",

journal = "Biometrics",

issn = "0006-341X",

publisher = "Oxford University Press",

number = "1",

}

TY - JOUR

T1 - A score test for testing a zero-inflated Poisson regression model against zero-inflated negative binomial alternatives

AU - Ridout, Martin

AU - Hinde, John

AU - DeméAtrio, Clarice G.B.

PY - 2001

Y1 - 2001

N2 - Count data often show a higher incidence of zero counts than would be expected if the data were Poisson distributed. Zero-inflated Poisson regression models are a useful class of models for such data, but parameter estimates may be seriously biased if the nonzero counts are overdispersed in relation to the Poisson distribution. We therefore provide a score test for testing zero-inflated Poisson regression models against zero-inflated negative binomial alternatives.

AB - Count data often show a higher incidence of zero counts than would be expected if the data were Poisson distributed. Zero-inflated Poisson regression models are a useful class of models for such data, but parameter estimates may be seriously biased if the nonzero counts are overdispersed in relation to the Poisson distribution. We therefore provide a score test for testing zero-inflated Poisson regression models against zero-inflated negative binomial alternatives.

KW - Count data

KW - Negative binomial

KW - Regression model

KW - Score test

KW - Zero inflation

UR - https://www.scopus.com/pages/publications/0035099098

U2 - 10.1111/j.0006-341X.2001.00219.x

DO - 10.1111/j.0006-341X.2001.00219.x

M3 - Article

SN - 0006-341X

VL - 57

SP - 219

EP - 223

JO - Biometrics

JF - Biometrics

IS - 1

ER -

A score test for testing a zero-inflated Poisson regression model against zero-inflated negative binomial alternatives

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this