有关巨灾风险中极值理论的研究.pdfVIP

摘 要 极值统计理论是数学的一个重要分支，主要研究随机事件极端情况的统计规 律性。巨灾风险的一般定义就是可能造成巨大财产损失和严重人员伤亡的风险。 巨灾风险一般具有损失程度高，发生概率小，损失的发生具有相对独立性等条件。 本文在第2章和第3章对极值理论做了简要的介绍。 对于极值理论，分布函数的尾部性质具有重要意义，而分布函数的极值指标 在刻画其尾部性质时起了很大的作用，并且极值分布大都呈现出重尾性质，因此 重尾情况下尾部极值指标的估计引起了人们的关注。许多学者提出了各种方法， 给出了很多不同的估计，本文在第4章总结前人研究的基础上，在第5章给出了对 于极值指标的新型估计。 在第6章和第7章，本文讨论用广义极值分布和广义Pareto分布拟合我国地震 损失数据，为我国的巨灾风险精算提供了一个坚实的数理基础，并探讨了巨灾债 券的定价，为研究我国巨灾风险提供参考。 Abstract Extreme statistics is an important branch of the main events on extreme cases of random statistical regularity. Catastrophe risk is literally understanding may cause enormous property losses and the risk of serious casualties. As a catastrophe risk generally require a high degree of loss, the probability of small, the loss occurred with relative independence, and other conditions. The extreme value index of distribution function plays an important role in describing the properties of tails, and extreme distribution mostly presets heavy tailed. Therefore the estimation of tail index for heavy tailed distribution have aroused our attention. Many scholars propose several methods, and get many different estimators. In this paper, the author will present a new method based on the outcomes of pre-researchers. In this paper, fitting use of generalized extreme value distribution and generalized Pareto distribution losses in China earthquake data to determine the earthquake losses in excess of the distribution of forms. So as to the catastrophic risk of insurability laid a solid mathematical foundation, for the research of China’s catastrophic risk reference. 目 录 第一章 引言…………………………………………………………………… 1 1.1 巨灾风险概述 ……………………………………………………………1 1.2 极值