Talk:Control chart/Archives/2013
![]() | This is an archive of past discussions. Do not edit the contents of this page. If you wish to start a new discussion or revive an old one, please do so on the current talk page. |
Veracity and Lack of Citation
"While Dr. Shewhart drew from pure mathematical statistical theories, he understood data from physical processes typically produce a "normal distribution curve" (a Gaussian distribution, also commonly referred to as a "bell curve"). "
This should be taken out, unless there is a specific citation for proposition that "he understood" what is being claimed. On the face of it is wrong because normality isn't required to use a control chart, and because its not actually true, e.g. any process which is "not in statistical control" is de facto not a normal distribution!69.250.186.253 (talk) —Preceding undated comment added 14:10, 4 May 2012 (UTC).
A process can be perfectly normal and out of statistical control if it excedes both of the desired limits defining control range. Example, pH data excedes upper and lower limits by the same degree and an even number of times. Either way, not sure comment is critical to scope of this article.
Joe Jirka (talk) 18:07, 26 December 2012 (UTC)
I question the wording that "application of the charts in the presence of such [non normality] increases the... type I and type II error rates of the control charts." Having a limit off one way or the other can never increase both type II and type I. I suppose the opposite end of the distribution may experience a Type II crisis, whenever the extreme tail end experiences a Type I crisis. This could be clarified as "type I or type II" and then a sentence added that eliminates some head scratching by the reader. — Preceding unsigned comment added by 144.15.255.227 (talk) 19:58, 22 February 2013 (UTC)
Shewhart set 3-sigma (3-standard error) limits on the following basis
Shewhart set 3-sigma (3-standard error) limits on the following basis
Didn't he actually do empirical experiments. I.e. he drew chips from a bowl.
So shouldn't there be a fourth bullet something like: experimentation
Untitled
This article should not be merged. Control charts are a related but very clearly separate issue from the common and special causes from which they arise. -- Phil 20:39, 14 December 2005 (UTC)