Process Capability (Cp, Cpk) and Process

Performance (Pp, Ppk) – What is the

Difference?
In the Six Sigma quality methodology, process performance is reported to the organization as a sigma level. The

higher the sigma level, the better the process is performing.

Another way to report process capability and process performance is through the statistical measurements of Cp, Cpk,

Pp, and Ppk. This article will present definitions, interpretations and calculations for Cpk and Ppk though the use of

forum quotations. Thanks to everyone below that helped contributed to this excellent reference.

Jump To The Following Sections:

 Definitions

 Interpreting Cp, Cpk

 Interpreting Pp, Ppk

 Differences Between Cpk and Ppk

 Calculating Cpk and Ppk

Definitions

Cp= Process Capability. A simple and straightforward indicator of process capability.

Cpk= Process Capability Index. Adjustment of Cp for the effect of non-centered distribution.

Pp= Process Performance. A simple and straightforward indicator of process performance.

Ppk= Process Performance Index. Adjustment of Pp for the effect of non-centered distribution.

Interpreting Cp, Cpk

“Cpk is an index (a simple number) which measures how close a process is running to its specification limits, relative

to the natural variability of the process. The larger the index, the less likely it is that any item will be outside the

specs.” Neil Polhemus

“If you hunt our shoot targets with bow, darts, or gun try this analogy. If your shots are falling in the same spot forming

a good group this is a high Cp, and when the sighting is adjusted so this tight group of shots is landing on the

bullseye, you now have a high Cpk.” Tommy

“Cpk measures how close you are to your target and how consistent you are to around your average performance. A

person may be performing with minimum variation, but he can be away from his target towards one of the

specification limit, which indicates lower Cpk, whereas Cp will be high. On the other hand, a person may be on

average exactly at the target, but the variation in performance is high (but still lower than the tolerance band (i.e.,

specification interval). In such case also Cpk will be lower, but Cp will be high. Cpk will be higher only when you r

meeting the target consistently with minimum variation.” Ajit

“You must have a Cpk of 1.33 [4 sigma] or higher to satisfy most customers.” Joe Perito

“Consider a car and a garage. The garage defines the specification limits; the car defines the output of the process. If

the car is only a little bit smaller than the garage, you had better park it right in the middle of the garage (center of the

specification) if you want to get all of the car in the garage. If the car is wider than the garage, it does not matter if you

have it centered; it will not fit. If the car is a lot smaller than the garage (Six Sigma process), it doesn’t matter if you

park it exactly in the middle; it will fit and you have plenty of room on either side. If you have a process that is in

control and with little variation, you should be able to park the car easily within the garage and thus meet customer

requirements. Cpk tells you the relationship between the size of the car, the size of the garage and how far away from

the middle of the garage you parked the car.” Ben

“The value itself can be thought of as the amount the process (car) can widen before hitting the nearest spec limit

(garage door edge).

Cpk =1/2 means you’ve crunched nearest the door edge (ouch!)

Cpk =1 means you’re just touching the nearest edge

Cpk =2 means your width can grow 2 times before touching

Cpk =3 means your width can grow 3 times before touching” Larry Seibel

Interpreting Pp, Ppk

“Process Performance Index basically tries to verify if the sample that you have generated from the process is

capable to meet Customer CTQs (requirements). It differs from Process Capability in that Process Performance only

applies to a specific batch of material. Samples from the batch may need to be quite large to be representative of the

variation in the batch. Process Performance is only used when process control cannot be evaluated. An example of

this is for a short pre-production run. Process Performance generally uses sample sigma in its calculation; Process

capability uses the process sigma value determined from either the Moving Range, Range or Sigma control charts.”

Praneet
Differences Between Cpk and Ppk

“Cpk is for short term, Ppk is for long term.” Sundeep Singh

“Ppk produces an index number (like 1.33) for the process variation. Cpk references the variation to your specification

limits. If you just want to know how much variation the process exhibits, a Ppk measurement is fine. If you want to

know how that variation will affect the ability of your process to meet customer requirements (CTQ’s), you should use

Cpk.” Michael Whaley

“It could be argued that the use of Ppk and Cpk (with sufficient sample size) are far more valid estimates of long and

short term capability of processes since the 1.5 sigma shift has a shaky statistical foundation.” Eoin

“Cpk tells you what the process is CAPABLE of doing in future, assuming it remains in a state of statistical control. Ppk

tells you how the process has performed in the past. You cannot use it predict the future, like with Cpk, because the

process is not in a state of control. The values for Cpk and Ppk will converge to almost the same value when the

process is in statistical control. that is because sigma and the sample standard deviation will be identical (at least as

can be distinguished by an F-test). When out of control, the values will be distinctly different, perhaps by a very wide

margin.” Jim Parnella

“Cp and Cpk are for computing the index with respect to the subgrouping of your data (different shifts, machines,

operators, etc.), while Pp and Ppk are for the whole process (no subgrouping). For both Ppk and Cpk the ‘k’ stands for

‘centralizing facteur’ – it assumes the index takes into consideration the fact that your data is maybe not centered

(and hence, your index shall be smaller). It is more realistic to use Pp and Ppk than Cp or Cpk as the process variation

cannot be tempered with by inappropriate subgrouping. However, Cp and Cpk can be very useful in order to know if,

under the best conditions, the process is capable of fitting into the specs or not.It basically gives you the best case

scenario for the existing process.” Chantal

“Cp should always be greater than 2.0 for a good process which is under statistical control. For a good process under

statistical control, Cpk should be greater than 1.5.” Ranganadha Kumar

“As for Ppk/Cpk, they mean one or the other and you will find people confusing the definitions and you WILL find books

defining them versa and vice versa. You will have to ask the definition the person is using that you are talking to.” Joe

Perito
“I just finished up a meeting with a vendor and we had a nice discussion of Cpk vs. Ppk. We had the definitions exactly

reversed between us. The outcome was to standardize on definitions and move forward from there. My suggestion to

others is that each company have a procedure or document (we do not), which has the definitions of Cpk and Ppk in it.

This provides everyone a standard to refer to for WHEN we forget or get confused.” John Adamo

“The Six Sigma community standardized on definitions of Cp, Cpk, Pp, and Ppk from AIAG SPC manual page 80. You

can get the manual for about $7.” Gary

Calculating Cpk and Ppk

“Pp = (USL – LSL)/6*Std.dev

Cpl = (Mean – LSL)/3*Std.dev

Cpu = (USL – Mean)/3*Std.dev

Cpk= Min (Cpl, Cpu)” Ranganadha Kumar

“Cpk is calculated using an estimate of the standard deviation calculated using R-bar/d2. Ppk uses the usual form of

the standard deviation ie the root of the variance or the square root of the sum of squares divided by n – 1. The R-

bar/D2 estimation of the standard deviation has a smoothing effect and the Cpk statistic is less sensitive to points

which are further away from the mean than is Ppk.” Eoin

“Cpk is calculated using RBar/d2 or SBar/c4 for Sigma in the denominator of you equation. This calculation for Sigma

REQUIRES the process to be in a state of statistical control. If not in control, your calculation of Sigma (and hence

Cpk) is useless – it is only valid when in-control.” Jim Parnella

“You can have a ‘good’ Cpk yet still have data outside the specification, and the process needs to be in control before

evaluating Cpk.” Matt

 Statistical Process Control
(SPC)
Cp (capability process)

The Cp index describes process capability; it is the number of times the spread of the process fits into
the tolerance width. The higher the value of Cp, the better the process.

Example: if Cp = 2.5, the spread of the process fits 2½ times into the tolerance width, while Cp = 1
means that the spread is equal to the tolerance width.

Note that even if the spread is off-centre, it is still the same size (Cp index). The figure takes no
account of where the spread is positioned in relation to the upper and lower tolerance limits, but
simply expresses the relation ship between the width of the spread and the tolerance width (see Fig.
3).

Read more about capability »

HomeWhat is SPC?Why use SPC?Recommended readingFAQGlossaryContact

Cm (capability machine)

The Cm index describes machine capability; it is the number of times the spread of the machine fits
into the tolerance width. The higher the value of Cm, the better the machine.

Example: if Cm = 2.5, the spread fits 2½ times into the tolerance width, while Cm = 1 means that the
spread is equal to the tolerance width.

Note that even if the spread is off-centre, it is still the same size (Cm index). The figure takes no
account of where the spread is positioned in relation to the upper and lower tolerance limits, but
simply expresses the relation ship between the width of the spread and the tolerance width (see Fig.
1).

Read more about capability »

Cpk (capability process index)

If you also want to study the position of the process in relation to the tolerance limits, you use the Cpk
index, which describes the process capability corrected for position. It is not much use having a high
Cp index if the process setting is way off centre in relation to the middle of the tolerance range.

A high Cpk index means, then, that you have a good process with a small spread in relation to the
tolerance width, and also that it is well centred within that width. If Cpk is equal to Cp, the process is
set to produce exactly in the middle of the tolerance range (see Fig. 4).

A normal requirement is that Cpk should be at least 1.33.

Read more about capability »

Cmk (capability machine index)

If you also want to study the position of the machine’s capability in relation to the tolerance limits, you
use the Cmk index, which describes the capability corrected for position. It is not much use having a
high Cm index if the machine setting is way off centre in relation to the middle of the tolerance range.

A high Cmk index means, then, that you have a good machine with a small spread in relation to the
tolerance width, and also that it is well centred within that width. If Cmk is equal to Cm, the machine
is set to produce exactly in the middle of the tolerance range (see Fig. 2).

A normal requirement is that Cmk should be at least 1.67.

Read more about capability »

Control limits

Control limits are an important aspect of statistical process control. They have nothing to do with
tolerance limits, because they are designed to call your attention when the process changes its
behaviour.

An important principle is that control limits are used along with the mean value on the control graph
to control the process, unlike tolerance limits, which are used along with individual measurements to
determine whether a given part meets specifications or not.

The function of control limits is to centre the process on the target value, which is usually the same as
the middle of the tolerance width, and to show where the limit of a stable process lies. This means, in
principle, that you have no reason to react until the control chart signals certain behaviour.

A commonly used control graph is the XR graph, where the position and spread of the process are
monitored with the help of sub groups and control limits.

If a point falls outside a control limit on the X graph, the position of the process has changed (see Fig.
16).

If a point falls outside a control limit on the R graph, the spread of the process has changed (see Fig.
17).
The six factors

These are the factors that are generally regarded as causing variation in capability measurements:

 Machine (e.g. degree of wear and choice of tooling);

 Measurement (e.g. resolution and spread of measuring instrument);
 Operator (e.g. how experienced and careful he/she is);
 Material (e.g. variations in surface smoothness and hardness);
 Environment (e.g. variations in temperature, humidity and voltage);
 Method (e.g. type of machining operation).

Centring value for target value

This is the distance from the target value T to the mean value of the machine or process spread (the
hump on the normal distribution curve), expressed as a percentage of the tolerance width (see Fig.
10).

There is less talk of centring value for target value nowadays, but the maximum permitted deviation
used to be in the region of TO +15%.

Go to top

Go to top

Go to top

Go to top

Go to top
Normal distribution curve

Also called the bell curve because of its shape, this is the pattern in which measurement readings are
distributed in most cases as a result of random variations about the mean value (the highest point on
the hump, see Fig. 11).

Note that most of the readings are grouped near the hump; the farther out toward the edges, the
fewer the readings. In other words it is not very likely that you will find any components at all giving
widely deviant readings when making normal spot-check measurements. So it is not enough that the
components you happen to measure are all within the tolerances.

It takes measurements of a large number of components to determine the size and shape of the bell
curve, and that can be time-consuming. But the standard deviation offers you a shortcut!

Read about the standard deviation »

Capability

Machine capability
Machine capability is measured in Cm and Cmk; it is a snapshot picture that shows how well a
machine is performing right now in relation to the tolerance limits. Figure 6 shows some examples.

When measuring machine capability you must not alter machine settings or change tools, materials,
operators or measurement methods, stop the machine, etc. In other words: Out of the six factors,
only machine and measurement are allowed to affect the result.

Read more about The six factors »

Go to top
Process capability
Process capability is a long-term study, measured in Cp and Cpk, that shows how well a process is
performing in relation to the tolerance limits while the study is in progress, as well as indicating likely
performance in the immediate future.

You could say that process capability is the sum of a index of machine capabilities measured over a
period of time (see Fig. 7).

When measuring process capability, you must include everything that affects the process, i.e. all six
factors.

Read more about The six factors »

Machine capability Process capability

Index Cm and Cmk Cp and Cpk

Factors influencing result Machine & measurement All six factors

Stoppages Not to be included Included

Adjustments Not to be included Included

No. of components 20–50 in succession 50–250

Time Short Long

Standard deviation

One standard deviation

This is a statistical function used to calculate the normal distribution curve, for example. The
procedure is that you measure the distance from the mean value (highest point on the hump) to the
point where the curve changes direction and starts to swing outward. This distance constitutes one
standard deviation (see Fig. 14).

This means that you do not need to measure hundreds of components to find out how much the
machine or process is varying. Instead you can calculate the spread using the standard deviation (see
below).
Six standard deviations
To calculate the normal distribution spread, you simply multiply the standard deviation by 6 to get the
total width of the normal distribution curve. If you had gone on making measurements you could have
plotted the curve, but now you have calculated it instead (see Fig. 15).

The normal distribution curve is thus derived from one standard deviation and consists of six of them.
These six account for 99.73% of the actual result. That also means that 0.27% of the outcome is not
included in the normal distribution curve.

Go to top
Target value

Imagine a shaft fitted in a round hole.

If the diameter of the shaft is on the large side, it leaves less-than-optimum room for lubricant
between the shaft and the hole. This results in poorer lubrication, faster wear and shorter lifetime.

A smallish diameter, on the other hand, means greater-than-optimum play. The play tends to increase
faster, which also shortens lifetime.

The assembly works best at the target value T, which in this case is in the middle of the tolerance
range (see Fig. 8)

For unilateral properties such as run-out, surface smoothness or mechanical strength, the target value
is zero (see Fig. 9).

Statistical process control lets you centre your process on the target value.

Go to top

 Cm »
 Cmk »
 Cp »
 Cpk »
 The six factors »
 Capability »
 Target Value »
 Go to top

How are control limits determined?

The correct way is to let the control limits adapt to the process. That way, a smaller spread in the
process gives a narrower control zone, while a greater spread gives a wider control zone (see Fig. 18).

It is a widespread myth that this will cause the operator to adjust the process more often, but in
practice the reverse is true; the process is adjusted less often compared to operation without SPC. If
you let the control limits follow the process, you will react neither too early nor too late when the
behaviour of the process changes.

Other ways of determining control limits

In some cases there may be difficulties about letting the control limits adapt to the process. One such
case is where the process uses tools that are not easily adjustable, such as fixed reamers or punches.

Since such tools often produce very little variation in the process and therefore allow a narrow control
zone without the possibility of adjusting the tool, it may be better to cut the control limits loose from
the process and lock them to a given distance from the tolerance limits instead (see Fig. 19).

Go to top

Go to top

PPM (parts per million)

In a quality control context, PPM stands for the number of parts per million (cf. percent) that lie
outside the tolerance limits. Cpk 1.00 means that 2 700 PPM (0.27%) of the manufactured parts are
out of tolerance, while Cpk 1.33 means that 63 PPM (0.0063%) are rejects.
Note that the PPM index can be drastically improved by a relatively small improvement in the
capability index (see Fig. 12).

Go to top

Six Sigma

Six Sigma is a philosophy and a mindset for quality improvement used by companies and
organisations. The method focuses on minimising waste by minimising variations in processes.

In concrete terms, Six Sigma means that the company's processes maintain six standard deviations
from the mean value of the process to the nearest tolerance limit. It follows from this that Cpk 2.0
gives 6 sigma, while for example Cpk 1.33 gives 4 sigma (see Fig. 13).

Go to top

 Target value offset »

 Normal distribution curve »
 PPM »
 Six Sigma »
 Standard deviation »
 Control limits »
 Sub group »New
Sub group

A sub group consists of a number of individual measurements (normally three, four or five) made in
sequence from a process. The mean value of these sub- groups, like the process itself, follows a
normal distribution curve (see Fig. 20).

Mean values show much less variation compared to individual measurements. This fact, combined with
control limits which follow the process in a control graph, means that the machine operator no longer
over reacts compared to when adjustment of the process is based on individual measurements. The
operator will therefore, as a rule, both measure and adjust the process less often, while at the same
time quality will be better.

Read about control limits »

Go to top