Testing for overdispersion in a censored Poisson regression model

Byoung Cheol Jung; Myoungshic Jhun; Seuck Heun Song

doi:10.1080/02331880601012884

Testing for overdispersion in a censored Poisson regression model

Byoung Cheol Jung, Myoungshic Jhun, Seuck Heun Song

Department of Statistics

Korea University

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

6 Scopus citations

Abstract

In this article, we investigate the efficiency of score tests for testing a censored Poisson regression model against censored negative binomial regression alternatives. Based on the results of a simulation study, score tests using the normal approximation, underestimate the nominal significance level. To remedy this problem, bootstrap methods are proposed. We find that bootstrap methods keep the significance level close to the nominal one and have greater power uniformly than does the normal approximation for testing the hypothesis.

Original language	English
Pages (from-to)	533-543
Number of pages	11
Journal	Statistics
Volume	40
Issue number	6
DOIs	https://doi.org/10.1080/02331880601012884
State	Published - 1 Dec 2006

Keywords

Bootstrap
Censored count data
Negative binomial
Poisson regression model
Score test

Access to Document

10.1080/02331880601012884

Cite this

@article{72bb19c7f4cc49148889cd59e215f4d5,

title = "Testing for overdispersion in a censored Poisson regression model",

abstract = "In this article, we investigate the efficiency of score tests for testing a censored Poisson regression model against censored negative binomial regression alternatives. Based on the results of a simulation study, score tests using the normal approximation, underestimate the nominal significance level. To remedy this problem, bootstrap methods are proposed. We find that bootstrap methods keep the significance level close to the nominal one and have greater power uniformly than does the normal approximation for testing the hypothesis.",

keywords = "Bootstrap, Censored count data, Negative binomial, Poisson regression model, Score test",

author = "Jung, {Byoung Cheol} and Myoungshic Jhun and Song, {Seuck Heun}",

year = "2006",

month = dec,

day = "1",

doi = "10.1080/02331880601012884",

language = "English",

volume = "40",

pages = "533--543",

journal = "Statistics",

issn = "0233-1888",

publisher = "Taylor and Francis Ltd.",

number = "6",

}

TY - JOUR

T1 - Testing for overdispersion in a censored Poisson regression model

AU - Jung, Byoung Cheol

AU - Jhun, Myoungshic

AU - Song, Seuck Heun

PY - 2006/12/1

Y1 - 2006/12/1

N2 - In this article, we investigate the efficiency of score tests for testing a censored Poisson regression model against censored negative binomial regression alternatives. Based on the results of a simulation study, score tests using the normal approximation, underestimate the nominal significance level. To remedy this problem, bootstrap methods are proposed. We find that bootstrap methods keep the significance level close to the nominal one and have greater power uniformly than does the normal approximation for testing the hypothesis.

AB - In this article, we investigate the efficiency of score tests for testing a censored Poisson regression model against censored negative binomial regression alternatives. Based on the results of a simulation study, score tests using the normal approximation, underestimate the nominal significance level. To remedy this problem, bootstrap methods are proposed. We find that bootstrap methods keep the significance level close to the nominal one and have greater power uniformly than does the normal approximation for testing the hypothesis.

KW - Bootstrap

KW - Censored count data

KW - Negative binomial

KW - Poisson regression model

KW - Score test

UR - http://www.scopus.com/inward/record.url?scp=33751520480&partnerID=8YFLogxK

U2 - 10.1080/02331880601012884

DO - 10.1080/02331880601012884

M3 - Article

AN - SCOPUS:33751520480

SN - 0233-1888

VL - 40

SP - 533

EP - 543

JO - Statistics

JF - Statistics

IS - 6

ER -

Testing for overdispersion in a censored Poisson regression model

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this