Confidence Regions for High Quantiles of A Heavy Tailed Distribution
主 题: Confidence Regions for High Quantiles of A Heavy Tailed Distribution
报告人: Prof. Yongcheng Qi (University of Minnesota Duluth)
时 间: 2005-11-21 下午 4:00-5:00
地 点: 理科一号楼 1560
Estimating high quantiles plays an important role in the context of risk management. This involves extrapolating of an unknown distribution function. In this talk we propose three methods,.i.e., the normal approximation method, the likelihood ratio method and the data tilting method, to construct confidence regions for high quantiles of a heavy tailed distribution. A simulation study prefers the data tilting method.