國立政治大學統計學系
學 術 演 講
主講人：Prof. Arthur B. Yeh 葉百堯教授 Department of Applied Statistics and Operations Research,
Bowling Green State University
題 目：A Nonparametric Phase I Control Chart for Monitoring
Location Parameter Based on Empirical Likelihood Ratio
時 間：民國111年6月27日 (星期一) 上午11：00
地 點：國立政治大學商學院260903教室
摘 要：
One common challenge in non-manufacturing control chart applications is that many of the quality characteristics to be monitored are not normally distributed. In these applications, normal transformation of the observations is certainly feasible; however, it will be done at the expense of the interpretability of the analysis which is particularly important to control chart users in non-manufacturing industries.
Most of the existing nonparametric control charts are designed for Phase II monitoring. Little has been done in developing nonparametric Phase I control charts especially for individual observations which are prevalent in non-manufacturing applications. In this work, we propose a new nonparametric Phase I control chart for monitoring the location parameter whose construction is essentially based on the empirical likelihood ratio test. The performance of the proposed chart, in terms of the signal probability, compares favorably with the recently developed charts for individual observations. A non-manufacturing example is included in which the proposed chart and the other competing charts are applied and compared.
