A score test for zero-inflation in multilevel count data

Authors:
Abbas Moghimbeigi;Mohammad Reza Eshraghian;Kazem Mohammad;Brian McArdle
Affiliations:
Department of Biostatistics and Epidemiology, School of Public Health and Center for Health Research, Hamadan University of Medical Sciences, Iran;Department of Epidemiology and Biostatistics, Tehran University of Medical Sciences, Iran;Department of Epidemiology and Biostatistics, Tehran University of Medical Sciences, Iran;Department of Statistics, University of Auckland, New Zealand
Venue:
Computational Statistics & Data Analysis
Year:
2009

Citing 3
Cited 2

Zero-inflated Poisson regression, with an application to defects in manufacturing

Technometrics
On estimation of the Poisson parameter in zero-modified Poisson models

Computational Statistics & Data Analysis
Score tests for zero-inflated Poisson models

Computational Statistics & Data Analysis

An extension of an over-dispersion test for count data

Computational Statistics & Data Analysis
Score tests for zero-inflation and overdispersion in two-level count data

Computational Statistics & Data Analysis

Quantified Score

Hi-index	0.03

Visualization

Abstract

The zero-inflated Poisson regression (ZIP) in many situations is appropriate for analyzing multilevel correlated count data with excess zeros. In this paper, a score test for assessing ZIP regression against Poisson regression in multilevel count data with excess zeros is developed. The sampling distribution and power of the score statistic test is evaluated using a simulation study. The results show that under a wide range of conditions, the score statistic performs satisfactorily. Finally, the use of the score test is illustrated on DMFT index data of children 7-8 years old.