Bayesian Sampling.

Abstract

A prediction-interval approach was derived for determining Gaussian sampling plans for finite lots required to be of very high quality. The plans are such that a lot is rejected if a single defective item is found in the sample. No loss function is required for the implementation of the plans, so they may be used in any situation in which the manufacturing process is Gaussian and lots are small (less than 100 items) and required to be of high quality. The savings in sample size over traditional attribute plans or variables plans assuming an infinite lot size is considerable.

Document Details

Document Type
Technical Report
Publication Date
Feb 28, 1975
Accession Number
ADA006592

Entities

People

  • K. W. Fertig
  • N. R. Mann

Organizations

  • Rocketdyne

Tags

DTIC Thesaurus Topics

  • Intervals
  • Sampling

Readers

  • Regression Analysis.

Technology Areas

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