🚀 go-pugleaf

 Kwenda mzuri, responded to my admitedly down-and-dirty,
go-for-the-throat, simplistic post on the Cp/Cpk thread with:
> While this is certainly true, many such characteristics are quite well
> modeled by the Folded-normal or Rayleigh distributions. These
> distributions are well-characterized and a Cp, if necessary can be
> readily derived without recourse to the specious assumption that the data
> are normally distributed.
=======================
There may be a bit of misunderstanding here.  Wheeler's empircal rule
goes into great detail to explain that there is NO assumption about
the normality of the distribution when you use the empircal rule.  He
specifically discusses how it applies if the distribution is not
normal and uses six distinct non-normal distributions to make his
point.
=========================

and. . . .

> Such an invocation is quite unnecessary. If the data are unimodal and
> apparently non-normal, Chebycheff's inequality will serve quite well to
> make a reasoned estimate of the upper (or lower) limit of the
> distribution. If the data are bimodal (or worse) then some serious,
> additional analysis must take place before reporting any capability index.

I appreciate the input and supect that all that he says is true.  My
point in responding as I did, is that there is a strong liklihood (at
least in my mind) that the original poster, or certainly many list
members, do not know, care nor have the time to care about the REAL
way to answer the question.  They have about 15 minutes (the
attention span of the Top Dog when it comes to questions of Quality
and statistics) to give an answer.

In my 35+ years in manufacturing I have NEVER run accross a Plant
Manager or even a VP of Mfg. (other than at a Quality Seminar) that
had any understanding of even the most basic concepts of SPC much
less capability indices.  I have run accross maybe three (3) Quality
Managers that did.  My point is that as simplistic as it is,
Wheeler's empirical rule will be more than accurate enough for many
industrial purposes and that it is a tool that is available for
anyone who made it through high school algebra.

In some cases the world is probably better served by the Quality
professional using his/her disposable time to work on the
psycho/political dimension of SPC and Quality rather than
spinning their wheels with arcane statistical methods, that while
valid, etc. are beyond the needs of the person asking the questions.
In so much of industry (at least the parts of it I am familiar with)
a "good enough" answer is a significant breakthrough.

This has come out with a bit more "edge" than I intended.  My point
is that one's employer and Quality in general can be well served by
some very simple approaches.  Where you and your boss are at
determines where the answer needs to come from.  I am sure that in
some places referring to the empircal rule would not be acceptable
which is why the more detailed responses are of value.



<< All opinions, statements, &c are my own>>
L.H. Garlinghouse, C.Q.E.
Pocahontas AR U.S.A.
(870) 892-4586  ext 7659
garlinghou@waterlooindustries.com