Tests for the Extreme Value and Weibull Distributions Based on Normalized Spacings.

Abstract

In this article we compare tests of the null hypothesis HO that a sample, which may be censored at one or both ends, comes from an extreme-value distribution with unknown location and scale parameters; such tests can also be used to test that observations come from a Weibull distribution with origin zero, and scale and shape parameters unknown. Such tests of HO are important in many applications, in particular in reliability theory and survival analysis.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 19, 1985
Accession Number
ADA163566

Entities

People

  • F. O'reilly
  • M. A. Stephens
  • R. A. Lockhart

Organizations

  • Stanford University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Accuracy
  • Data Science
  • Distribution Theory
  • Information Science
  • Military Research
  • Normal Distribution
  • Observation
  • Order Statistics
  • Probability
  • Random Variables
  • Reliability
  • Standards
  • Statistical Samples
  • Statistics
  • Survival
  • United States
  • United States Government

Fields of Study

  • Mathematics

Readers

  • Statistical inference.

Technology Areas

  • Space