Improving extremal fit: a Bayesian regularization procedure

被引：6

作者：

Diebolt, J

Garrido, M

Trottier, C

机构：

[1] Univ Montpellier 3, F-34199 Montpellier 5, France

[2] INRIA Rhone Alpes, IS2 Project, F-38334 Saint Ismier, France

[3] Univ Paris 12, CNRS, F-77454 Marne La Vallee 2, France

来源：

RELIABILITY ENGINEERING & SYSTEM SAFETY | 2003年 / 82卷 / 01期

关键词：

goodness-of-fit tests; tail distribution; rare events; extreme test; upper quantile; mixture of distributions;

D O I：

10.1016/S0951-8320(03)00096-6

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

In structural reliability, special attention is devoted to model distribution tails. The distributions are required to fit the upper observations and provide a picture of the tail above the maximal observation. Goodness-of-fit tests can be constructed to check this tail fit. Then what can we do with distributions having a good central fit and a bad extremal fit? We propose a regularization procedure. It is based on Bayesian tools and takes into account the opinion of experts. Predictive distributions are proposed as model distributions. We numerically investigate this method on normal, lognormal, exponential, gamma and Weibull distributions. (C) 2003 Elsevier Ltd. All rights reserved.

引用

页码：21 / 31

页数：11