Efficient inference and simulation for elliptical Pareto processes

• 成果类型: Article
• 署名作者: Thibaud, Emeric; Opitz, Thomas
• 署名单位: Colorado State University System; Colorado State University Fort Collins; INRAE
• 刊物名称: BIOMETRIKA
• ISSN/ISSBN: 0006-3444
• DOI: 10.1093/biomet/asv045
• 发表日期: 2015
• 页码: 855870
• 关键词: DISTRIBUTIONS

摘要

Recent advances in extreme value theory have established l-Pareto processes as the natural limits for extreme events defined in terms of exceedances of a risk functional. In this paper we provide methods for the practical modelling of data based on a tractable yet flexible dependence model. We introduce the class of elliptical l-Pareto processes, which arise as the limits of threshold exceedances of certain elliptical processes characterized by a correlation function and a shape parameter. An efficient inference method based on maximizing a full likelihood with partial censoring is developed. Novel procedures for exact conditional and unconditional simulation are proposed. These ideas are illustrated using precipitation extremes in Switzerland.