Likelihood-based confidence interval for the ratio of scale parameters of two independent Weibull distributions

J. Wu, A. C.M. Wong, K. W. Ng

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

The Weibull distribution is widely used in lifetime data analysis. For example, in studies on the time to the occurrence of tumors in human populations or in laboratory animals, the time of occurrence of tumors is generally assumed to be distributed as a Weibull distribution. Moreover, in engineering, the voltage levels at which failure occurred in electrical cable insulation has been shown to be distributed as a Weibull distribution. When comparing two independent Weibull distributions, it is often assumed that only the scale parameter is altered. In this paper, we propose a simple and accurate procedure to obtain inference concerning the ratio of the two scale parameters of two independent distributions. The performance of the proposed method is assessed through Monte Carlo simulation studies. The numerical results show that the proposed method is extremely accurate even for very small samples. The method is applied to a set of real-life data.

Original languageEnglish
Pages (from-to)487-497
Number of pages11
JournalJournal of Statistical Planning and Inference
Volume135
Issue number2
DOIs
StatePublished - Dec 1 2005

Bibliographical note

Funding Information:
The first author's research was supported in part by the National Cancer Center support grant CA21765 and American Lebanese Syrian Associated Charities (ALSAC). The second author's research was supported in part by NSERC.

Keywords

  • Confidence interval
  • Coverage probability
  • Extreme value distribution
  • Signed log-likelihood ratio
  • Weibull distribution
  • r* formula

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Likelihood-based confidence interval for the ratio of scale parameters of two independent Weibull distributions'. Together they form a unique fingerprint.

Cite this