Robust Confidence intervals for a Scale Parameter: A Compromise between the Gaussian and the Slash.

Abstract

This report describes a small sample approach parallel to the one for a location parameter. Derived (MORGENTHALER (1983 1, 1983b). We derive is the form of conditional confidence distribution for log(delta) = tau and then discussed are the difficulties in compromising the Gaussian and the slash. Explored are both the strong and the bi-optimal procedures. And it becomes clear that there is a difference between inference about location and inference about scale. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1983
Accession Number
ADA143666

Entities

People

  • S. Morgenthaler

Organizations

  • Princeton University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Analysis Of Variance
  • Data Analysis
  • Data Science
  • Deficiencies
  • Estimators
  • Information Science
  • Intervals
  • Military Research
  • New Jersey
  • New York
  • Probability
  • Random Variables
  • Standards
  • Statistical Analysis
  • Statistics
  • Universities

Fields of Study

  • Mathematics

Readers

  • Neurological Diseases/Conditions/Disorders
  • Regression Analysis.

Technology Areas

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