5. How can we refine the detection of abnormal variations?
It is possible to refine the detection of statistical signals, corresponding to variations that are not "noise", by using additional rules, such as :
Three out of four successive points are closer to a limit than to the average.
Eight successive points are on the same side of the average.
If you detect that your process has moved towards a new equilibrium, don't hesitate to calculate the new variation parameters (which is possible as soon as 5 or 6 points are available).
The Ultimate Scientific and Technical Reference
This article is included in
Quality manager
This offer includes:
Knowledge Base
Updated and enriched with articles validated by our scientific committees
Services
A set of exclusive tools to complement the resources
Practical Path
Operational and didactic, to guarantee the acquisition of transversal skills
Doc & Quiz
Interactive articles with quizzes, for constructive reading
How can we refine the detection of abnormal variations?
Generalize for large production runs
Bibliography
Also in our database
Bibliography
Deming, Hors de la Crise , Éditions Economica
Shewhart, Les fondements de la maîtrise de la qualité , Éditions Economica
Wheeler, Understanding variations , Éditions SPC Press (Very didactic book, detailing concrete examples from the management of industrial companies. I have borrowed from this author the terms "natural process limits",...
ToolWebsites
Association française Edwards Deming
Website of the Association Française Edwards Deming. This site offers a biography of Deming, as well as a series of free resources on Deming: a selection of articles, e-books and statistical software. You'll also find a French translation of Western Electric's Manual of Statistical Quality Control....
The Ultimate Scientific and Technical Reference
