K Simultaneous Measurement Procedures: A Bayesian Approach.

Abstract

When several instruments are used to measure an observed response the accuracy depends on the variance of the distribution of responses and of instrument errors. The problem considered in this paper is estimation of these variances and of certain ratios called relative precisions. The authors adopt a Bayesian approach in attacking the problem and apply a prior distribution to the parameters, proposed by Jeffreys, to obtain the relevant posterior distributions. To illustrate the applicability of these results, some data on burning times of fuses used in projectile firings is analyzed to yield point and interval estimates of the parameters of interest. Areas in which this research might be applied are those in which accuracy and relative precision play an important role, (e.g. instrumentation) rather than those in which substantial variability is present (e.g. agricultural trials) but a comparison of mean values is the main concern. (Author)

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1975
Accession Number
ADA018004

Entities

People

  • Irwin Guttman
  • Norman Draper

Organizations

  • University of Wisconsin–Madison

Tags

Communities of Interest

  • Weapons Technologies

DTIC Thesaurus Topics

  • Accuracy
  • Bayesian Networks
  • Errors
  • Instrumentation
  • Intervals
  • Measurement
  • Measuring Instruments
  • Precision
  • Projectiles
  • Yield Strength

Fields of Study

  • Mathematics

Readers

  • Astronomy and Astrophysics.
  • Economics
  • Statistical inference.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference