A Bayesian Approach to Capability Testing Based on Cpk with Multiple Samples

Process capability indices provide numerical measures to compare the output of a process to client's expectations. However, most of the existing researches have used traditional distribution frequency method by using a single sample due to assess process capability. An alternative to this appro...

Full description

Saved in:
Bibliographic Details
Published in:Quality and reliability engineering international 2014-07, Vol.30 (5), p.615-621
Main Authors: Kargar, M., Mashinchi, M., Parchami, A.
Format: Article
Language:English
Subjects:
Bayesian approach
capability testing
multiple samples
posterior probability
process capability indices
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Process capability indices provide numerical measures to compare the output of a process to client's expectations. However, most of the existing researches have used traditional distribution frequency method by using a single sample due to assess process capability. An alternative to this approach is to use the Bayesian method. In this paper, we utilize a Bayesian approach based on subsamples to check process capability via capability index Cpk. As a new suggestion, we used the informative normal prior distribution and the characteristics of sufficient statistic of the parameter to drive the posterior distribution. The capability test is done, and the posterior probability p, for which the process under investigation is capable, is derived both based on the most popular index Cpk. Finally, a numerical example is given to clarify the method. Copyright © 2013 John Wiley & Sons, Ltd.
ISSN:0748-8017
1099-1638
DOI:10.1002/qre.1512