A Bayesian spatially-clustered coefficient model with temporal structures for hepatitis A data in South Korea

Hepatitis A, a highly contagious and perilous viral liver infection, is globally widespread, with its data collected across spatial and temporal domains. Also, demographic and socioeconomic covariates, such as population density and per capita income, are gathered over space and time units. As a result, the association between infectious disease outcomes and risk factors may differ across space and time. Some sub-regions may have a heterogeneous association with others, while a homogeneous temporal structure may exist within certain sub-regions. Acknowledging the potential variability in these associations, this study focused on comprehending the spatio-temporal dynamics of hepatitis A through a statistical model. In this paper, we analyzed monthly hepatitis A infection counts in the Republic of Korea from January 2020 to December 2021 using a Bayesian spatio-temporal model. Specifically, we employed a Bayesian spatially-clustered coefficient model with temporal structures to estimate sub-regions with the temporally varying risk effects associated with hepatitis A. Our focus lies in utilizing the Bayesian spatio-temporal model to uncover insights into the spatio-temporally varying relationships between covariates and hepatitis A outcomes. Furthermore, we addressed the spatial confounding bias prevalent in common spatial models with space-time random components by incorporating two-stage framework within our analysis.