Multivariate zero-and-one inflated Poisson model with applications

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS

卷:365

Article

Zhang, Chi¹  Tian, Guo-Liang²  Yuen, Kam Chuen³  Wu, Qin⁴  Li, Tao⁵ 

[1] Shenzhen Univ, Coll Econ, Nanhai Ave 3688, Shenzhen 518060, Guangdong, Peoples R China

[2] Southern Univ Sci & Technol, Dept Stat & Data Sci, 1088 Xueyuan Rd, Shenzhen 518055, Guangdong, Peoples R China

[3] Univ Hong Kong, Dept Stat & Actuarial Sci, Pokfulam Rd, Hong Kong, Peoples R China

[4] South China Normal Univ, Sch Math Sci, Dept Stat, Guangzhou 510631, Guangdong, Peoples R China

[5] Southern Univ Sci & Technol, Dept Math, 1088 Xueyuan Rd, Shenzhen 518055, Guangdong, Peoples R China

关键词: Expectation-maximization (EM) algorithm;    Multivariate zero-and-one inflated poisson;    Univariate zero-and-one inflated poisson;    Zero-inflated poisson;   

DOI  :  10.1016/j.cam.2019.112356

来源: Elsevier

【 摘 要 】

This paper extends the univariate zero-and-one inflated Poisson (ZOIP) distribution (Melkersson & Olsson, 1999; Zhang et al., 2016) to its multivariate version, which can be used to model correlated multivariate count data with large proportions of zeros and ones marginally. More importantly, this new multivariate ZOIP distribution possesses a flexible dependency structure: i.e., the correlation coefficient between any two random components could be either positive or negative depending on the values of the parameters. The important distributional properties are explored and some useful statistical inference methods without and with covariates are developed. Simulation studies are conducted to evaluate the performance of the proposed methods. Finally, two real data sets on healthcare and insurance are used to illustrate the proposed methods. (C) 2019 Elsevier B.V. All rights reserved.

【 授权许可】

Free