A Selection Procedure Using a Screening Variate.

Abstract

Consider N objects on which two correlated measurements X and Y can be made. Assume that the probability that the Y measurement meets a certain specification is gamma. We present a method whereby a maximal subset of m out of the N objects can be chosen, based on the observed X measurements, so that there is a high probability that a large proportion of the selected subset will meet the desired specification related to the Y measurement. The method we propose uses the conditional probabilities that Y will meet the specification given by the observed value of the x's. The procedure compared favorably with one suggested by Owen, Chen, and Li but has the advantage that no special tables are needed. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 1980
Accession Number
ADA083902

Entities

People

  • Richard W. Madsen

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Inequalities
  • Mathematics
  • Measurement
  • Military Research
  • Missouri
  • Normal Distribution
  • Order Statistics
  • Probability
  • Random Variables
  • Specifications
  • Standards
  • Statistics
  • Universities

Fields of Study

  • Mathematics

Readers

  • Regression Analysis.