Extreme value theory (EVT) provides an elegant mathematical tool for statistically analyzing rare events. When data are collected from multiple population subgroups, the scientific interest of researchers would generally be to improve the estimates obtained directly from each subgroup because some subgroups may have less data available for extreme value analysis. To achieve this, we incorporate the mixed effects model (MEM) into the regression technique in EVT. In small area estimation, the MEM has attracted considerable attention as a primary tool for providing reliable estimates for subgroups with small sample sizes, that is, ``small area.'' The key idea of the MEM is to incorporate information from all subgroups into a single model and to borrow strength from other subgroups to improve estimates by subgroup. Using this property, the MEM may contribute to reducing the bias and variance of the direct estimates for each subgroup, which result from the asymptotic specification of EVT. This prompts us to evaluate MEM's effectiveness in EVT through theoretical studies and numerical experiments, including its application to assessing the risk of heavy rainfall in Japan.
翻译:暂无翻译