A simulation-based hyperparameter selection for quantile estimation of the generalized extreme value distribution

被引：17

作者：

Park, JS ^{[1
]}

机构：

[1] Chonnam Natl Univ, Dept Stat, Kwangju 500757, South Korea

来源：

MATHEMATICS AND COMPUTERS IN SIMULATION | 2005年 / 70卷 / 04期

基金：

新加坡国家研究基金会;

关键词：

beta distribution; hydrology; maximum likelihood estimation; L-moment estimation; penalized likelihood; shape parameter;

D O I：

10.1016/j.matcom.2005.09.003

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 [计算机应用技术]; 0835 [软件工程];

摘要：

A systematic way of selecting hyperparameters of the prior on the shape parameter of the generalized extreme value distribution (GEVD) is presented. The optimal selection is based on a Monte Carlo simulation in the generalized maximum likelihood estimation (GMLE) framework. A scaled total misfit measure for the accurate estimation of upper quantiles is used for the selection criterion. The performance evaluations for GEVD and non-GEVD show that the GMLE with selected hyperparameters produces more accurate quantile estimates than the MLE, the L-moments estimator, and Martins-Stedinger's GMLE. (c) 2005 IMACS. Published by Elsevier B.V. All rights reserved.

引用

页码：227 / 234

页数：8

共 10 条

[1]

Coles S. G., 1999, Extremes, V2, P5, DOI [10.1023/A:1009905222644, DOI 10.1023/A:1009905222644]

[2]

Efron B., 1994, INTRO BOOTSTRAP, DOI DOI 10.1201/9780429246593

[3]

Maximum likelihood parameter estimation by model augmentation with applications to the extended four-parameter generalized gamma distribution [J].