Int. J Sup. Chain. Mgt Vol. 8, No. 6, December, 2019 1175 Bayesian Group Chain Sampling Plan Based on Beta Binomial Distribution through Quality Region Waqar Hafeez 1 , Nazrina Aziz *2 1,2 School of Quantitative Sciences, College of Arts and Sciences, Universiti Utara Malaysia, 06010 Sintok, Kedah, Malaysia 1 waqarhafeez78601@gmail.com *2 nazrina@uum.edu.my Abstract— In this article, we introduced Bayesian Group Chain Sampling Plan (BGChSP) using different combination of parameters. In acceptance sampling plan, the random fluctuations can be describe in the selection of distribution Bayesian approach which is based on prior process history. We apply beta distribution as a suitable prior distribution. By considering consumer’s and producer’s risks, we consider Probabilistic and Indifference Quality Regions for the specified AQL and LQL. For the selection of parameters in BGChSP, Maximum Allowable Percent Defectives (MAPD) is also considered. Keywords— acceptance sampling plan, binomial, beta distribution, quality region, consumer’s risks, producer’s risk, acceptance quality level, limiting quality level. 1. Introduction Bayesian acceptance sampling approach is based on the combination of lot information and the prior information for the selection of distribution. To describe the random variation, Bayesian approach required to specify from lot to lot a distribution of defectives. Prior distribution is the expected distribution of a lot quality, that is going for inspection. This distribution is formulated before taking the sample, so it is called prior. The empirical knowledge is based on sample under study is called sample distribution or data distribution. The combination of prior and empirical information’s leads to take decision about lot. For Bayesian sampling inspection a statistical model considers the following three components: 1. The prior distribution must according to quality of the submitted lot. 2. Sampling inspection cost on acceptance and rejection. 3. On the base of mean rejection, a class is designed in the sampling plans, to give acceptance protection against a poor quality lot. The sampling plans based on economic consider different factors to design a cost effect plan: like cost of inspection rejecting a conforming product and accepting a non-conforming product. The history of similar lots that already submitted for inspection are count in to the Bayesian sampling plan. Non- Bayesian sampling methodology does not based on past history. There is tough competition in industry by rapidly increasing in the needs of statistical and analytical techniques towards the improvement of product quality. This study is related to BGChSP by using a novel approach called quality region or quality interval sampling (QIS). Instead of point this plan is based on quality range. This plan delivers decision rules of acceptance for both supplier and customer to meet the present quality condition of the product. Improvement in the technology is rapidly increasing with the passage of time and supplier needs high quality products with low defective fraction. Unfortunately, in some particular situation traditional methods can not detect out defect in the product. QIS was introduced to overcome such problems. By involving QIS, this article designs the parameters for the plan indexed with quality region. For inspection Chain sampling plan was introduced by Dodge [1]. Under an assumption that cost is linear in p that is fraction of defective; Hald [2] provide a system attribute single sampling plan obtain by minimizing average cost. By using gamma ______________________________________________________________ International Journal of Supply Chain Management IJSCM, ISSN: 2050-7399 (Online), 2051-3771 (Print) Copyright © ExcelingTech Pub, UK (http://excelingtech.co.uk/)