Information in Censored Models.

Abstract

Criteria are developed for measuring information in the randomly right-censored model. Measures which are appropriate include an extension of Shannon's entropy. The measures are seen to satisfy some fundamental theorems including (i) the uncensored case is always at least as informative as any censored model, (ii) information decreases as censoring increases stochastically, and (iii) the information gain is marginally decreasing. Additional keywords: random variables; statistical inference.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1985
Accession Number
ADA158644

Entities

People

  • Frank Proschan
  • J. Sconing
  • M. Hollander

Organizations

  • Florida State University

Tags

DTIC Thesaurus Topics

  • Air Force
  • Censorship
  • Classification
  • Discrete Distribution
  • Models
  • New York
  • Observation
  • Probability
  • Probability Distributions
  • Random Variables
  • Scientific Research
  • Security
  • Statistical Estimation
  • Statistical Inference
  • Statistics
  • Theorems
  • Universities

Fields of Study

  • Mathematics

Readers

  • Statistical inference.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms