Ppk versus Cpk
Six Sigma – iSixSigma › Forums › Old Forums › General › Ppk versus Cpk
 This topic has 3 replies, 4 voices, and was last updated 17 years, 11 months ago by Reigle Stewart.

AuthorPosts

June 30, 2004 at 1:40 pm #36027
We are having a lot of heated discussions about the difference between Ppk and Cpk and when you should use each. I have searched the web several times and found conflicting opinions and definitions of each! Can anyone help? Thanks!
0June 30, 2004 at 1:45 pm #102684The definitions used in Six Sigma come from the AIAG SPC manual (page 79 – 81). Minitab is programed using the definitions given there.
0June 30, 2004 at 2:32 pm #102689MiniTab accepted definition used in my company is:
Cpk, Process Capability, often referred to as Short term capability, the potential (within) capability indices are associated with the withinsubgroup standard deviation. These indices reflect how the process could perform relative to the specification limits, if the shifts and drifts between subgroups could be eliminated. The calculation of Cpk in MiniTab takes in to account the effect of time ordering by using the observed level of variation taken from a Moving Range, Range or Sigma control charts.
Ppk, Process Performance, often referred to as Long term capability, the overall capability indices are associated with the overall sample standard deviation. These indices depict how the process is actually performing relative to the specification limits. Ppk is calculated by Minitab using the mathematical standard deviation of all the data. This is the figure that should be reported for Component Proving
A substantial difference between the overall and within capability indices may indicate that the process is out of control, or the sources of variation are not estimated by within capability. Ppk will always be less than or equal to Cpk because the process spread predicted by Ppk will always be larger than (or equal to) as it does not take into account the time ordered behaviour of the process.
Just to complicate the issue the definitions are reversed in some texts!
0June 30, 2004 at 3:00 pm #102691
Reigle StewartParticipant@ReigleStewart Include @ReigleStewart in your post and this person will
be notified via email.Sgollus: To help answer your question, I refer you to the
“Ask Dr. Harry” forum on this site. He states: “One must
necessarily understand that the shortterm standard
deviation reports on the instantaneous reproducibility of
a process whereas the longterm standard deviation
reflects the sustainable reproducibility. To this end, the
shortterm standard deviation is comprised of the within
group sumsofsquares (SSW). The longterm standard
deviation incorporates the total sumsofsquares (SST).
Of course, the difference between the two constitutes the
between group sumsofsquares (SSB). By employing a
rational sampling strategy it is possible to effectively block
the noises due to assignable causes from those due to
random causes. In this context, we recognize that SST =
SSW + SSB. By considering the degreesoffreedom
associated with SST and SSW, we are able to compute
the corresponding variances and then establish the
respective standard deviations. In the case of a process
characterization study, we note that the shortterm
standard deviation is given by the quantity Sqrt(SSW / g(n
1)). The longterm standard deviation is defined as
Sqrt(SST / ng 1). When computing Cp and Cpk, it is
necessary to employ the shortterm standard deviation.
This ensures that the given index of capability reports on
the instantaneous reproducibility of the process under
investigation. So as to reflect the sustainable
reproducibility of the process, the longterm standard
deviation must be employed to compute Pp and Ppk.
Oddly enough, many practitioners confuse these two
overlapping sets of performance indices.”0 
AuthorPosts
The forum ‘General’ is closed to new topics and replies.