Minimum message length inference of the Weibull distribution with complete and censored data

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

The Weibull distribution, with shape parameter k> 0 and scale parameter λ> 0, is one of the most popular parametric distributions in survival analysis. It is well established that the maximum likelihood estimate of the Weibull shape parameter is inadequate due to the associated large bias when the sample size is small or the proportion of censored data is large. This manuscript demonstrates how the Bayesian information-theoretic minimum message length principle, coupled with a suitable choice of weakly informative prior distributions, can be used to infer Weibull distribution parameters given either complete data or data with censoring. Empirical experiments show that the proposed minimum message length estimate of the shape parameter is superior to the maximum likelihood estimate and is competitive with other recently proposed modified maximum likelihood estimates in terms of Kullback-Leibler risk.

Original languageEnglish
Title of host publicationAI 2023: Advances in Artificial Intelligence - 36th Australasian Joint Conference on Artificial Intelligence, AI 2023 Brisbane, QLD, Australia, November 28 – December 1, 2023 Proceedings, Part I
EditorsTongliang Liu, Geoff Webb, Lin Yue, Dadong Wang
Place of PublicationSingapore Singapore
PublisherSpringer
Pages291-303
Number of pages13
ISBN (Electronic)9789819983889
ISBN (Print)9789819983872
DOIs
Publication statusPublished - 2024
EventAustralasian Joint Conference on Artificial Intelligence 2023 - Brisbane, Australia
Duration: 28 Nov 20231 Dec 2023
Conference number: 36th
https://link.springer.com/book/10.1007/978-981-99-8388-9 (Proceedings)
https://ajcai2023.org/ (Website)

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume14471
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceAustralasian Joint Conference on Artificial Intelligence 2023
Abbreviated titleAJCAI 2023
Country/TerritoryAustralia
CityBrisbane
Period28/11/231/12/23
Internet address

Keywords

  • model selection
  • parameter estimation
  • Weibull distribution

Cite this