Bayesian Two-Sided Complete Group Chain Sampling Plan (BT-SCGChSP) for Binomial Distribution Using Beta Prior Through Quality Regions

Bayesian Two-Sided Complete Group Chain Sampling Plan

Abstract

Acceptance sampling is a technique of statistical quality assurance based on inspection of a random sample items and making a decision about the lot in which it is either accepted or rejected. In the case of available historical knowledge, experts say that the Bayesian approach is the best approach to making a correct decision. In this study, for the average probability of acceptance, a Bayesian two-sided complete group chain sampling plan (BT-SCGChSP) is proposed. The binomial distribution is used to derive the probability of lot acceptance and beta distribution is used as a prior distribution. Four quality regions, namely (i) quality decision region (QDR), (ii) probabilistic quality region (PQR), (iii) limiting quality region (LQR) and (iv) indifference quality region (IQR) are considered for consumer and producer risks. For selecting parameters in BT-SCGChSP, acceptable quality level (AQL) and limiting quality level (LQL) are also considered. The values are extracted for BT-SCGChSP based on different combinations of design parameters are tabulated and inflection point values are derived. Operating characteristic curves are used to make compression with the existing plan and the finding exposes that BT-SCGChSP is a better substitute in industrial practitioners in certain product life research sectors.