良率的信賴區間估計

Abstract

在工業上，良率為生產產品之品質特性落在規格界限內的比例。當我們假設良品的個數服從二項分配時，那麼建造良率的信賴區間是一個在工業應用中很重要的過程。在這項研究中，我們提出了一個方法，以改善現有良率之信賴區間估計。我們設法建立了一個程序來計算所提出的區間之覆蓋率下界。而模擬研究則提供了在不同的區間下去比較各種區間的優點與缺點。

Proportion of conformance is defined as the proportion of products with quality characteristic inside the specification limits. The construction of confidence interval for proportion of conformance is an important problem in industrial applications, especially when the number of conforming units follows a binomial distribution. In this study, we propose an approach to improve the existing confidence intervals for proportion of conformance. We establish a procedure to calculate the lower bound for the coverage probability of proposed the intervals. A simulation study is provided to compare the performance of different intervals.