|
|
"Hanspi" <hanspi@xxxxxxxxxxxxxxxx> wrote in news:1146206426.856322.163920
@j73g2000cwa.googlegroups.com:
> So my joke was better than I thought. Tell me one thing, though: with
> 6 sigma, I would get a failure probability of 1.97E-9, the 3.4E-6 would
> only be 4.6 sigma; so "six sigma" stands for "+- 4.6 sigma"? Why is
> then "3.4 defects per million opportunities" used in the "six sigma"
> concept?
>
>
There is a 1.5 S.D. fudge factor that the SS "theoreticians" have thrown
in. See:
http://www.isixsigma.com/library/content/c010101a.asp
<quote>
__Many processes are prone to being influenced by special and/or
assignable causes that impact the overall performance of the process
relative to the customer's specification. That is, the overall
performance of our process as the customer views it might be 3.4 DPMO
(corresponding to Long Term performance of 4.5 Sigma). However, our
process could indeed be capable of producing a near perfect output (Short
Term capability ? also known as process entitlement ? of 6 Sigma). The
difference between the "best" a process can be, measured by Short Term
process capability, and the customer's aggregate experience (Long Term
capability) is known as Shift depicted as Zshift or sshift. For a
"typical" process, the value of shift is 1.5; therefore, when one hears
about "6 Sigma," inherent in that statement is that the short term
capability of the process is 6, the long term capability is 4.5 (3.4 DPMO
? what the customer sees) with an assumed shift of 1.5. Typically, when
reference is given using DPMO, it denotes the Long Term capability of the
process, which is the customer's experience. The role of the Six Sigma
professional is to quantify the process performance (Short Term and Long
Term capability) and based on the true process entitlement and process
shift, establish the right strategy to reach the established performance
objective. <end=quote>
--
David Winsemius
|
|