Multivariate zero-inflated Bell–Touchard distribution for multivariate counts: An application to COVID-related data

Abstract

Multivariate count data with an excessive number of zeros occur commonly in practice. To deal with this kind of data, we introduce a simple and tractable parametric multivariate zero-inflated distribution, which corresponds to a multivariate extension of the univariate zero-inflated Bell–Touchard distribution. Various distributional properties are derived and, in particular, the marginal distributions are univariate zero-inflated Bell–Touchard distributions. The unknown parameters of the proposed multivariate zero-inflated distribution are estimated using the maximum likelihood estimation procedure. An empirical application that employs COVID-related real data is provided to illustrate the new multivariate zero-inflated distribution in practice, and comparison with some multivariate zero-inflated distributions is made.