Analysis of over-dispersed count data with extra zeros using the Poisson log-skew-normal distribution

被引:3
作者
Hassanzadeh, Fatemeh [1 ]
Kazemi, Iraj [1 ]
机构
[1] Univ Isfahan, Dept Stat, Hezarjerib, Isfahan, Iran
关键词
Gaussian quadrature; Lambert's W function; mixed Poisson; skew-normal distribution; zero-inflated distributions; 60E05; 62J12; 65C60; REGRESSION; MODEL; OVERDISPERSION; DEMAND;
D O I
10.1080/00949655.2015.1117086
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Mixed Poisson distributions are widely used in various applications of count data mainly when extra variation is present. This paper introduces an extension in terms of a mixed strategy to jointly deal with extra-Poisson variation and zero-inflated counts. In particular, we propose the Poisson log-skew-normal distribution which utilizes the log-skew-normal as a mixing prior and present its main properties. This is directly done through additional hierarchy level to the lognormal prior and includes the Poisson lognormal distribution as its special case. Two numerical methods are developed for the evaluation of associated likelihoods based on the Gauss-Hermite quadrature and the Lambert's W function. By conducting simulation studies, we show that the proposed distribution performs better than several commonly used distributions that allow for over-dispersion or zero inflation. The usefulness of the proposed distribution in empirical work is highlighted by the analysis of a real data set taken from health economics contexts.
引用
收藏
页码:2644 / 2662
页数:19
相关论文
共 46 条
[11]  
BRESLOW NE, 1984, J R STAT SOC C-APPL, V33, P38
[12]   FITTING POISSON LOGNORMAL DISTRIBUTION TO SPECIES-ABUNDANCE DATA [J].
BULMER, MG .
BIOMETRICS, 1974, 30 (01) :101-110
[14]  
Deb P, 1997, J APPL ECONOMET, V12, P313, DOI 10.1002/(SICI)1099-1255(199705)12:3<313::AID-JAE440>3.0.CO
[15]  
2-G
[16]   A Poisson mixed model with nonnormal random effect distribution [J].
Fabio, Lizandra C. ;
Paula, Gilberto A. ;
de Castro, Mario .
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2012, 56 (06) :1499-1510
[17]   A discrete version of the half-normal distribution and its generalization with applications [J].
Gomez-Deniz, E. ;
Vazquez-Polo, F. J. ;
Garcia-Garcia, V. .
STATISTICAL PAPERS, 2014, 55 (02) :497-511
[18]   A comparison between the discrete Poisson-gamma and Poisson-lognormal distributions to characterise microbial counts in foods [J].
Gonzales-Barron, Ursula ;
Butler, Francis .
FOOD CONTROL, 2011, 22 (08) :1279-1286
[19]  
Greene William., 2005, Foundations and Trends in Econometrics, V1, P113, DOI DOI 10.1561/0800000008
[20]   Modelling count data with overdispersion and spatial effects [J].
Gschloessl, Susanne ;
Czado, Claudia .
STATISTICAL PAPERS, 2008, 49 (03) :531-552