Talk:Statistical process control/Archives/2011

Poor example

Final paragraph:

SPC indicates when an action should be taken in a process, but it also indicates when NO action should be taken. An example is a person who would like to maintain a constant body weight and takes weight measurements weekly. A person who does not understand SPC concepts might start dieting every time his or her weight increased, or eat more every time his or her weight decreased. This type of action could be harmful and possibly generate even more variation in body weight. SPC would account for normal weight variation and better indicate when the person is in fact gaining or losing weight."

fails to illustrate the use of SPC as an indicator of when it's appropriate to take no action. Could this example be improved? —Preceding unsigned comment added by 118.168.108.176 (talk) 08:19, 5 January 2009 (UTC)

thanks. —Preceding unsigned comment added by 152.132.10.134 (talk) 19:02, 13 October 2010 (UTC)

What does the following extract mean ? This should be clarified or linked to supporting info.

The criticalness of the process can be defined by the westinghouse rules used.

The only way to reduce natural variation is through improvement to the process technology, see Nelson Funnel experiment. —Preceding unsigned comment added by 47.166.133.25 (talk) 18:07, 1 September 2009 (UTC)

The 'How to use SPC' section needs to outline that the data used to calculate mean and sigma must be from the process when it is known to be in control - generally it is not sufficient to take untested historical data. The process of establishing control can bring significant gain. —Preceding unsigned comment added by 94.193.145.39 (talk) 11:14, 2 February 2010 (UTC)

This is a common misconception about control charts, and is generally not true for X-bar R or XmR (ImR) charts. See discussion by Shewhart, Wheeler and others on this matter. The March 30, 2011 article by Davis Balestracci in Quality Digest directly attacks this myth, though with minimal discussion.

The purpose of Process Control Charts is to provide a means of detecting when the process is likely out of control. It is not generally possible to determine that a process is in control and there are few—perhaps no—more robust methods of identifying out-of-control signals than the control charts themselves. Use them to screen any data to detect nonhomogeneity (i.e. "out of control" signals). Tom Hopper (talk) 07:48, 5 April 2011 (UTC)

Modification of Western Electric Rules

Paragraph moved from article:

In practise, most people (in a manufacturing environment) will think of SPC as a set of rules and a control chart (paper and / or digital). SPC ought to be a PROCESS, that is, when conditions change such 'rules' should be re-evaluated and possibly updated. This does not, alas, take place usually; as a result the set of rules known as "the Western Electric rules" can be, with minor variations, found in a great many different environs (for which they are very rarely actually suitable).

Appears to present one side of a dispute or the opinions of the editor without reference to reputable sources. Needs improving per Wikipedia:NPOV and Wikipedia:Verifiability. Tom Hopper (talk) 07:17, 5 April 2011 (UTC)