Computational methods for a copula-based Markov chain model with a binomial time series

Abstract

This article provides supplementary information of Huang and Emura (2022).

Copula-based markov chain logistic regression modeling on binomial time series data

“…INAR(1) model with binomial time series data is known as the binomial AR(1) model. Binomial time series model has been well applied to several real problems, such as in the fields of finance and industry [4 , 5] . Huang & Emura (2022) used a copula-based Markov in modelling binomial time series to overcome the complexity and limitation of Binomial AR(1) [5] .…”

“…Binomial time series model has been well applied to several real problems, such as in the fields of finance and industry [4 , 5] . Huang & Emura (2022) used a copula-based Markov in modelling binomial time series to overcome the complexity and limitation of Binomial AR(1) [5] . Apart from that, the copula method has several advantages, namely capturing dependencies between two time series, being used flexibly for discrete bivariate distributions, and allowing for a negative correlation [3] .…”

“…Binomial time series models in [1 , 4 , 5] are proposed on univariate binomial time series data with probability . However, some data can be provided with covariate variables, which can be described as probability functions.…”