Transforming Censored Samples and Testing Fit.

Abstract

One approach to testing the goodness-of-fit of a completely specified continuous distribution with a censored sample, is to transform the corresponding uniform censored sample into a complete uniform sample and then to use any of the classical uniformity tests. Two systematic procedures for transforming a censored uniform sample are proposed. A Monte Carlo power study was conducted to analyze the relative merits of these procedures when followed by the Anderson-Darling A2 test for uniformity. The suggested transformations are versatile and with A2, give good power for most alternatives. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 23, 1985
Accession Number
ADA157957

Entities

People

  • F. J. O'reilly
  • M. A. Stephens

Organizations

  • Stanford University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Data Science
  • Distribution Functions
  • Goodness Of Fit Tests
  • Information Science
  • Intervals
  • Mathematics
  • Military Research
  • Observation
  • Order Statistics
  • Plastic Explosives
  • Probability
  • Random Variables
  • Statistics
  • United States
  • United States Government

Fields of Study

  • Mathematics

Readers

  • Statistical inference.