Testing the lack-of-fit of zero-inflated Poisson regression models

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

A zero-inflated Poisson regression model has been widely used for the effect of a covariate in count data containing many zeros with a linear predictor. To assess the adequacy of the linear relationship, we approximate the covariate effect with cubic B-splines. The semiparametric model parameters are estimated by maximizing the likelihood function through an expectation- maximization algorithm. A log-likelihood ratio test is then used to evaluate the adequacy of the linear relation. A simulation study is conducted to study the power performance of the test. A real example is provided to demonstrate the practical use of the methodology.

Original languageEnglish (US)
Pages (from-to)497-510
Number of pages14
JournalCommunications in Statistics: Simulation and Computation
Volume40
Issue number4
DOIs
StatePublished - Apr 2011

Fingerprint

Lack of Fit
Poisson Regression
Poisson Model
Covariates
Regression Model
Cubic B-spline
Log-likelihood Ratio
Testing
Count Data
Linear Relation
Semiparametric Model
Expectation-maximization Algorithm
Zero
Likelihood Ratio Test
Likelihood Function
Splines
Predictors
Simulation Study
Methodology
Evaluate

Keywords

  • B-splines
  • Expectation-maximization (EM) algorithm
  • Lack-of-fit test
  • Log-likelihood ratio test

ASJC Scopus subject areas

  • Modeling and Simulation
  • Statistics and Probability

Cite this

Testing the lack-of-fit of zero-inflated Poisson regression models. / Li, Chin-Shang.

In: Communications in Statistics: Simulation and Computation, Vol. 40, No. 4, 04.2011, p. 497-510.

Research output: Contribution to journalArticle

@article{58f1f9262b7548f99f4ce09c4bdd6fa6,
title = "Testing the lack-of-fit of zero-inflated Poisson regression models",
abstract = "A zero-inflated Poisson regression model has been widely used for the effect of a covariate in count data containing many zeros with a linear predictor. To assess the adequacy of the linear relationship, we approximate the covariate effect with cubic B-splines. The semiparametric model parameters are estimated by maximizing the likelihood function through an expectation- maximization algorithm. A log-likelihood ratio test is then used to evaluate the adequacy of the linear relation. A simulation study is conducted to study the power performance of the test. A real example is provided to demonstrate the practical use of the methodology.",
keywords = "B-splines, Expectation-maximization (EM) algorithm, Lack-of-fit test, Log-likelihood ratio test",
author = "Chin-Shang Li",
year = "2011",
month = "4",
doi = "10.1080/03610918.2010.546541",
language = "English (US)",
volume = "40",
pages = "497--510",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "4",

}

TY - JOUR

T1 - Testing the lack-of-fit of zero-inflated Poisson regression models

AU - Li, Chin-Shang

PY - 2011/4

Y1 - 2011/4

N2 - A zero-inflated Poisson regression model has been widely used for the effect of a covariate in count data containing many zeros with a linear predictor. To assess the adequacy of the linear relationship, we approximate the covariate effect with cubic B-splines. The semiparametric model parameters are estimated by maximizing the likelihood function through an expectation- maximization algorithm. A log-likelihood ratio test is then used to evaluate the adequacy of the linear relation. A simulation study is conducted to study the power performance of the test. A real example is provided to demonstrate the practical use of the methodology.

AB - A zero-inflated Poisson regression model has been widely used for the effect of a covariate in count data containing many zeros with a linear predictor. To assess the adequacy of the linear relationship, we approximate the covariate effect with cubic B-splines. The semiparametric model parameters are estimated by maximizing the likelihood function through an expectation- maximization algorithm. A log-likelihood ratio test is then used to evaluate the adequacy of the linear relation. A simulation study is conducted to study the power performance of the test. A real example is provided to demonstrate the practical use of the methodology.

KW - B-splines

KW - Expectation-maximization (EM) algorithm

KW - Lack-of-fit test

KW - Log-likelihood ratio test

UR - http://www.scopus.com/inward/record.url?scp=79952598382&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952598382&partnerID=8YFLogxK

U2 - 10.1080/03610918.2010.546541

DO - 10.1080/03610918.2010.546541

M3 - Article

AN - SCOPUS:79952598382

VL - 40

SP - 497

EP - 510

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 4

ER -