A Monte Carlo Study of Composite Sequential Likelihood Ratio Tests for the Weibull Scale Parameter.

Abstract

Three Sequential Likelihood Ratio Tests were constructed to choose between two values of the scale parameter (theta) of a Weibull distribution with a location parameter of zero, an unknown shape parameter (K) replaced by its maximum likelihood estimate, and error bounds of 0.05, 0.10, 0.15, and 0.20. The first two tests were based upon a general procedure for sequential tests for a parameter in the presence of a nuisance parameter by D. R. Cox in Sankhya A, Vol. 25. This method replaces the likelihood ratio with an asympotically equivalent test statistic. The tests were then truncated and the effects of this truncation upon the error bounds were studied.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1976
Accession Number
ADA035458

Entities

People

  • Richard L. Hoffert

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Computational Science
  • Computer Programs
  • Computers
  • Data Science
  • Distribution Functions
  • Information Processing
  • Information Science
  • Monte Carlo Method
  • New York
  • Normal Distribution
  • Probability
  • Probability Density Functions
  • Random Variables
  • Reliability
  • Statistical Algorithms
  • Statistics

Fields of Study

  • Mathematics

Readers

  • Statistical inference.