Author(s): Peter Madzík, Pavol Križo
Title: The Effect of Non-Normal Distributions on the Control Limits of X-Bar Chart
Source: International Scientific Days 2018 :: Towards Productive, Sustainable and Resilient Global Agriculture and Food Systems :: Proceedings
Publisher: Wolters Kluwer ČR, Prague
PY, pages: 2018, 851-862
Published on-line: 2018-11-09
Abstract: Shewhart control charts are often used by industry organizations for quality control. The most common diagram used is the X-bar chart, which monitors the progress of the mean of parameter over time.
For the use of control charts, practitioners a priori assume that the data has a normal distribution. The normality of data can be verified by various tests, but in practice, such verification is often circumvented.
If the data does not have a normal distribution, it will of course also affect the values of the control limits. This article aims to investigate the effect of selected types of distributions on the resulting control
limits in X-bar charts. The most common types of continuous distributions are analyzed and random data is used. The results point to the robustness of the control limits for some types of distributions and also to varying
impact on varying sub-group ranges and varying sample sizes.
Keywords: X-bar control charts, Contol Limits, Normality, Non-normality, Distributions
JEL Classification: L15, C15, C18, C46
Rights:Open Access :: Creative Commons BY-NC-SA 4.0 International Licence
Toto dielo je publikované pod/This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Licence.
Plný text/Fulltext (PDF)