Statistical Models for Studying the Incidence Rate of Deaths Among People Infected with COVID-19 in Southeast Asian (ASEAN) Countries

Abstract

The objective of this research is to study the relationship between countries in Southeast Asia (ASEAN), the total confirmed cases of COVID-19, the reproduction rate, the stringency index, and the new deaths attributed to COVID-19. Another purpose of this research is to find a suitable statistical model to study the incidence rate of deaths among people infected with COVID-19 in Southeast Asian countries (ASEAN). The online secondary data is used in this study, and the models considered are the Poisson regression model and the negative-binomial regression model. The results show that the Poisson regression model is unsuitable for the data used in this study because the variance of this data is significantly higher than its mean; this is called the overdispersion problem. On the other hand, the negative-binomial regression model is the most suitable model for studying the incidence rate of deaths among people infected with COVID-19 in Southeast Asian countries. Moreover, Thailand has been found to have a higher incidence rate of death from COVID-19 than other Southeast Asian countries; the incidence rate of death from COVID-19 in Cambodia, Indonesia, Laos, Malaysia, Philippines, Singapore, and Vietnam is lower than in Thailand by 99.5%, 99.4%, 28.1%, 99.4%, 72.0%, 99.7%, 56.0%, 97.9%, and 45.4%, respectively.