Comparison of methods of estimation for parameters of generalized Poisson distribution through simulation study

ABSTRACT In this article, we take a brief overview of different functional forms of generalized Poisson distribution (GPD) and various methods of its parameter estimation found in the literature. We compare the method of moment estimation (ME) and maximum likelihood estimation (MLE) of parameters of GPD through simulation study in terms of bias, MSE and covariance. To simulate random numbers from GPD, we develop a Matlab function gpoissrnd(). The simulation study leads to the important conclusion that the ME performs better or equally good as compared to MLE when sample size is small. Further we fit the GPD to various datasets in literature using both estimation methods and observe that the results do not differ significantly even though the sample size is large. Overall, we conclude that for GPD, use of ME in place of MLE will lead to almost similar results. The computational simplicity in calculation of ME as compared to MLE also gives support to the use of ME in case of GPD for practitioners.

[1]  consul P.C,et al.  Maximum likelihood estimation for the generalized poisson distribution , 1984 .

[2]  Estimation of Generalized Poisson Distribution by the Method of Weighted Discrepancies , 1992 .

[3]  Sudeep Srivastava,et al.  A two-parameter generalized Poisson model to improve the analysis of RNA-seq data , 2010, Nucleic Acids Research.

[4]  J. Hardin,et al.  A score test for overdispersion in Poisson regression based on the generalized Poisson-2 model , 2009 .

[5]  P. C. Consul,et al.  The generalized poisson distribution when the sample mean is larger than the sample variance , 1985 .

[6]  F. Famoye,et al.  A comparison of generalized Poisson distribution for modeling chromosome aberrations , 1996 .

[7]  A. W. Kepm.  Weighted discrepancies and maximum likelihood estimation for discrete distributions , 1986 .

[8]  Maximum likelihood estimation for the generalized poisson distribution when sample mean is larger than sample variance , 1988 .

[9]  T. Yee.  The VGAM Package for Categorical Data Analysis , 2010 .

[10]  P. Consul,et al.  On some interesting properties of the generalized POISSON distribution , 1973 .

[11]  Nabendu Pal,et al.  Zero-inflated Poisson (ZIP) distribution: parameter estimation and applications to model data from natural calamities , 2014 .

[12]  On negative moments of generalized poisson distribution , 1979 .

[13]  P. Consul,et al.  A Generalization of the Poisson Distribution , 1973 .

[14]  Generalized Poisson random variate generation , 1997 .

[15]  H. Tuenter.  On the generalized Poisson distribution , 2000, math/0606238.

[16]  F. Famoye,et al.  Generalized poisson regression model , 1992 .

[17]  L. Shenton,et al.  The distribution of a moment estimator for a parameter of the generalized poisson distribution , 1985 .

[18]  Eric R. Ziegel,et al.  Generalized Linear Models , 2002, Technometrics.

[19]  N. Ismail,et al.  Functional Form for the Generalized Poisson Regression Model , 2012 .

[20]  EDF Tests for the Generalized Poisson Distribution , 1999 .

[21]  Ilknur Özmen.  Quasi Likelihood/Moment Method for Generalized and Restricted Generalized Poisson Regression Models and Its Application , 2000 .

[22]  Jun Zhu,et al.  On the Generalized Poisson Regression Mixture Model for Mapping Quantitative Trait Loci With Count Data , 2006, Genetics.

[23]  On Applications of Some Probability Distributions , 2011 .

[24]  Alfred A. Bartolucci,et al.  A rich family of generalized Poisson regression models with applications , 2005, Math. Comput. Simul..

[25]  Carl Lee,et al.  Estimation of generalized poisson distribution , 1992 .

[26]  Gérard Letac,et al.  Natural Real Exponential Families with Cubic Variance Functions , 1990 .

[27]  Felix Famoye,et al.  On the Generalized Poisson Regression Model with an Application to Accident Data , 2004, Journal of Data Science.

[28]  F. Famoye,et al.  Modeling household fertility decisions with generalized Poisson regression , 1997, Journal of population economics.