Re: SPC Problem

["William J. Latzko" <latzko@worldnet.att.net>]

At 01:45 PM 3/4/2000 +0530, manoj@banas.guj.nic.in wrote:
>Daer Denizens,
>I have got a problem on SPC. If anyone can help me, please mail 
>the solution directly to my personal mail account;
>manoj@banas.guj.nic.in
>Problem: Method engineer has proposed to introduce modification 
>to change specification limit by 0.5 sigma on either side. What 
>considerations must have gone into, before proposing such a 
>change?What would be effect of this change on process capability. 
>As Quality Engineer what steps would you take to ensure that all 
>the production lots are accepted with these modified limits.
>Any solution ? Please help.

Dear Mr. Sharma

The methods engineer does not understand the purpose or use of a control
chart. The 3 sigma limits were set on the basis of an experiment by Dr.
Shewhart to find the most economic balance between two types of error that
one can commit in using the chart. To modify these limits can easily lead
to tampering with the system, i.e. to make changes when none are needed or
to fail to change when they are needed. 

I suggest that the engineer study Shewhart's original books. Unfortunately,
failure to do this has resulted in texts on control charts to give the
wrong impression. It is a case of Rule 4 of the funnel. The suggestion of
the methods engineer is already going out to the milky way.

Bill Latzko
----------------------------------------------------------------------------
--------------------
William J. Latzko                                    Voice: 201-868-5338
215 - 79th Street                               Facsimile: 201-868-5338
N. Bergen, NJ 07047                 E-mail:    latzko@worldnet.att.net
----------------------------------------------------------------------------
=========================================================================