Premium
An Extended Nonparametric Exponentially Weighted Moving Average Sign Control Chart
Author(s) -
Lu ShinLi
Publication year - 2015
Publication title -
quality and reliability engineering international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.913
H-Index - 62
eISSN - 1099-1638
pISSN - 0748-8017
DOI - 10.1002/qre.1673
Subject(s) - nonparametric statistics , control chart , ewma chart , chart , sign (mathematics) , statistical process control , statistics , normality , control limits , process (computing) , computer science , x bar chart , shewhart individuals control chart , mathematics , econometrics , mathematical analysis , operating system
Traditional control charts are established on the assumption that the observations of a process follow a normal or specific probability distribution. However, in many applications, there is insufficient information to justify this assumption. Thus, nonparametric control charts have been proposed in recent years and hold a significant place among statistical process control charts. Some of these charts are designed to monitor the location parameter, whereas others are available for the scale. The major advantage of these control charts is that the underlying process does not specifically assume normality or other specific distributions. In this paper, the nonparametric generally weighted moving average sign chart is developed to improve the detection capability in small process shifts. Simulation studies show that the nonparametric generally weighted moving average sign chart is not optimal in all scenarios but can compete with the nonparametric exponentially weighted moving average sign chart. Copyright © 2014 John Wiley & Sons, Ltd.