Quality measurement plan using Monte Carlo methods

Abstract

This study considers the Quality Measurement Plan (QMP), a system implemented for reporting the quality assurance audit results to Bell system management. QMP is derived from a new Bayesian approach to the empirical Bayes problem for Poisson observations. It uses both the current and past data to compute estimates for the quality of the current production. The QMP estimator developed by Hoadley in 1981 is based on many complicated approximations. Sampling approaches such as the Gibbs sampler and Importance-sampling are alternative techniques that avoid these approximations and permit the computation of the quality estimates through Monte Carlo methods. Here we discuss the approaches and the algorithms for implementing some Monte Carlo-based approaches on the QMP model. We also show via simulation that although the QMP algorithm can be computationally more convenient, the sampling approaches mentioned above give more accurate estimates of current quality.