Abstract
Acceptance sampling plans are practical tools for quality management applications and provide the producer and the consumer a general rule for lot sentencing to meet their requirements of product quality. There are several ways to classify acceptance sampling plans. One major classification is by attributes and variables, but attributes acceptance sampling plans no longer work since any sample of reasonable size probably contains no defective product items. However, variables acceptance sampling plans not only overcome the inconvenience of attributes acceptance sampling plans, but also have the same protection as attributes acceptance sampling plans would require less sampling. Several acceptance sampling plans have been developing by using different strategies, for example, repetitive group sampling plan (RGSP) and chain sampling plan (ChSP). RGSP is similar to that of the sequential sampling plan but it does not combine all the available information from the collected samples and might reduce the efficiency of inspection. ChSP considers the states of the preceding lots and can provide better efficiency of inspection, but the investigations of ChSP for variables were not completed. In this thesis, we first develop a variables chain sampling plan based on the most commonly capability index . Then, we further modify the RGSP by considering the concept of ChSP to develop a new sampling plan, called chain repetitive group sampling plan based on the index . Finally, we not only tabulate the plan parameters for various required quality levels and allowable risks are provided for practical applications, but also discuss the advantages of the proposed variables plans over than existing variables sampling plans.