PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

An introduction to a new way of eliciting prior distributions for Weibull inference in an inudstrial context
Nicolas BOUSQUET
Special Issue of the International Journal "Communications on Dependability and Quality Management in Engineering" 2005.

Abstract

This paper is focused on a new vision of the elicitation and the aggregation of prior distributions for the parameters of a Weibull model, when several experts can give their opinions. In many industrial durability/reliability contexts, there are only few censored lifetime data, and the Weibull model is the most popular lifetime model. So such a Bayesian integration is a important issue. Other relevant papers are summarized too.

Postscript - PASCAL Members only - Requires a viewer, such as GhostView
EPrint Type:Article
Additional Information:to be published
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:1994
Deposited By:Nicolas Bousquet
Deposited On:12 January 2006