Bayesian Acceptance Sampling for Attributes

This paper demonstrates the use of Bayesian methods in Acceptance Sampling for items which are categorized according to their attributes as defective or non defective, i.e binary (0-1) data. The main thrust of the paper is to account for the possibility of dependence among the items of a sample. An attempt has been made to incorporate the dependence structure in the acceptance sampling scheme. Two diierent Bayesian models have been proposed with a discussion of their advantages and shortcomings. Some of the common Acceptance Sampling measures for attributes like the Average Outgoing Quality (AOQ), Average Total Inspection (ATI), sampling costs, Operating Characteristic (OC) curve have been examined from a Bayesian viewpoint. Computation of such acceptance sampling measures are provided on simulated data using a sampling based approach based on Markov Chain Monte Carlo methods.