A Nonparametric Control Chart for Monitoring Individual Observations of Multiple Stream Processes Based on Cochran’s Q Test

• Activity Number: 344 - Contributed Poster Presentations: Quality and Productivity Section
• Type: Contributed
• Date/Time: Tuesday, August 9, 2022 : 2:00 PM to 3:50 PM
• Sponsor: Quality and Productivity Section
• Author(s): Austin Brown* and Bryce Whitehead
• Companies: Kennesaw State University and University of Northern Colorado
• Keywords: Quality Control; Multiple Stream Processes; Nonparametric

Abstract

In process monitoring applications, a commonly encountered scenario is one in which several presumably identical processes are desired to be monitored simultaneously. Such a process is referred to as a “Multiple Stream Process (MSP).” Several parametric control charts have been developed for monitoring MSPs with the majority being derived from the classical Shewhart X -bar chart. These control charts perform best when the assumption of normality is met, but their performance can deteriorate substantially when the underlying data are non-normal. This deterioration is magnified when the sample size is n=1. While some work has been done to address the issue of non-normality through the development of a nonparametric MSP chart, a review of the literature shows an apparent gap for nonparametric MSP charts where the sample size is one. Thus, this study aims to fill this gap by proposing a new nonparametric MSP chart based on the classical nonparametric test, Cohran’s Q Test. This chart utilizes the EWMA framework. Derivation of the charting statistic and control limits will be given as well as recommendations for selection of chart parameters for a desired average run length performance.