Zero-and-one-inflated Poisson regression model

In this paper, a zero-and-one-inflated Poisson (ZOIP) regression model is proposed. The maximum likelihood estimation (MLE) and Bayesian estimation for this model are investigated. Three estimation methods of the ZOIP regression model are obtained based on data augmentation method which is expectati...

Full description

Saved in:
Bibliographic Details
Published inStatistical papers (Berlin, Germany) Vol. 62; no. 2; pp. 915 - 934
Main Authors Liu, Wenchen, Tang, Yincai, Xu, Ancha
Format Journal Article
LanguageEnglish
Published Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2021
Springer Nature B.V
Subjects
Algorithms
Bayesian analysis
Computer simulation
Economic models
Economic Theory/Quantitative Economics/Mathematical Methods
Economics
Finance
Insurance
Management
Mathematics and Statistics
Maximization
Maximum likelihood estimation
Operations Research/Decision Theory
Optimization
Poisson density functions
Probability Theory and Stochastic Processes
Regression analysis
Regression models
Regular Article
Statistical analysis
Statistics
Statistics for Business
Data augmentation
Gibbs sampling
Zero-and-one-inflated Poisson regression model
EM algorithm
GEM algorithm
Online AccessGet full text

Cover

More Information
Summary:In this paper, a zero-and-one-inflated Poisson (ZOIP) regression model is proposed. The maximum likelihood estimation (MLE) and Bayesian estimation for this model are investigated. Three estimation methods of the ZOIP regression model are obtained based on data augmentation method which is expectation-maximization (EM) algorithm, generalized expectation-maximization (GEM) algorithm and Gibbs sampling respectively. A simulation study is conducted to assess the performance of the proposed estimation for various sample sizes. Finally, an accidental deaths data set is analyzed to illustrate the practicability of the proposed method.
ISSN:0932-5026
1613-9798
DOI:10.1007/s00362-019-01118-7