View Article - PDF     View Article - Webpage

Title: Some Comments on Control Charts with Large Subgroup Sizes
Author: Keith M. Bower
Publication Source: American Society for Quality, Six Sigma Forum, October 2004

Abstract

This article addresses the behavior of control chart sensitivity with increasing numbers of observations in a rational subgroup.

Notes

The argument at the heart of this paper - namely that larger subgroup sizes can (correctly) detect smaller changes in a process than otherwise is rather straightforward. I purposefully avoided a discussion of power and sample sizes, however, as I felt it may lead into a tangent on the relationship between control charting and hypothesis tests. For more information on that topic, I suggest reading Bill Woodall's paper from the American Society for Quality's Journal of Quality Technology.

To download Adobe Acrobat (for free) click here.