Process Capability Analysis in Minitab - Manual PDF

QCPRCAPA.
MK5 Page 1 Friday, December 17, 1999 12:52 PM
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
14
Process Capability
Process Capability Overview, 14-2
Capability Analysis (Normal Distribution), 14-6
Capability Analysis (Between/Within), 14-14
Capability Analysis (Weibull Distribution), 14-19
Capability Sixpack (Normal Distribution), 14-24
Capability Sixpack (Between/Within), 14-30
Capability Sixpack (Weibull Distribution), 14-34
Capability Analysis (Binomial), 14-37
Capability Analysis (Poisson), 14-41
MINITAB Users Guide 2
CONTENTS
14-1
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
QCPRCAPA.MK5 Page 2 Friday, December 17, 1999 12:52 PM
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
Chapter 14
HOW TO USE
Process Capability Overview

Once a process is in statistical control, that is producing consistently, you probably then
want to determine if it is capable, that is meeting specification limits and producing
good parts. You determine capability by comparing the width of the process variation
with the width of the specification limits. The process needs to be in control before you
assess its capability; if it is not, then you will get incorrect estimates of process capability.
You can assess process capability graphically by drawing capability histograms and
capability plots. These graphics help you assess the distribution of your data and verify
that the process is in control. You can also calculate capability indices, which are ratios
of the specification tolerance to the natural process variation. Capability indices, or
statistics, are a simple way of assessing process capability. Because they are unitless, you
can use capability statistics to compare the capability of one process to another.
Choosing a capability command

MINITAB provides a number of different capability analysis commands from which you
can choose depending on the the nature of data and its distribution. You can perform
capability analyses for:
Note
normal or Weibull probability models (for measurement data)
normal data that might have a strong source of between-subgroup variation
binomial or Poisson probability models (for attributes or count data)

If your data are badly skewed, you can use the Box-Cox transformation or use a Weibull
probability modelsee Non-normal data on page 14-6.
It is essential to choose the correct distribution when conducting a capability analysis.

For example, MINITAB provides capability analyses based on both normal and Weibull
probability models. The commands that use a normal probability model provide a more
complete set of statistics, but your data must approximate the normal distribution for
the statistics to be appropriate for the data.
For example, Capability Analysis (Normal) estimates expected parts per million
out-of-spec using the normal probability model. Interpretation of these statistics rests
on two assumptions: that the data are from a stable process, and that they follow an
approximately normal distribution. Similarly, Capability Analysis (Weibull) calculates
parts per million out-of-spec using a Weibull distribution. In both cases, the validity of
the statistics depends on the validity of the assumed distribution.
If the data are badly skewed, probabilities based on a normal distribution could give
rather poor estimates of the actual out-of-spec probabilities. In that case, it is better to
either transfom the data to make the normal distribution a more appropriate model, or
choose a different probability model for the data. With MINITAB, you can use the
14-2
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
Box-Cox power transformation or a Weibull probability model. Non-normal data on

page 14-6 compares these two methods.
If you suspect that there may be a strong between-subgroup source of variation in your
process, use Capability Analysis (Between/Within) or Capability Sixpack (Between/
Within). Subgroup data may have, in addition to random error within subgroups,
random variation between subgroups. Understanding both sources of subgroup
variation may provide you with a more realistic estimate of the potential capability of a
process. Capability Analysis (Between/Within) and Capability Sixpack (Between/Within)
computes both within and between standard deviations and then pools them to
calculate the total standard deviation.
MINITAB also provides capability analyses for attributes (count) data, based on the
binomial and Poisson probability models. For example, products may be compared
against a standard and classified as defective or not (use Capability Analysis (Binomial)).
You can also classify products based on the number of defects (use Capability Analysis
(Poisson)).
MINITABs capability commands
Capability Analysis (Normal) draws a capability histogram of the individual

measurements overlaid with normal curves based on the process mean and standard
deviation. This graph helps you make a visual assessment of the assumption of
normality. The report also includes a table of process capability statistics, including
both within and overall statistics.
Capability Analysis (Between/Within) draws a capability histogram of the

individual measurements overlaid with normal curves, which helps you make a visual
assessment of the assumption of normality. Use this analysis for subgroup data in
which there is a strong between-subgroup source of variation, in addition to the
within-subgroup variation. The report also includes a table of between/within and
overall process capability statistics.
Capability Analysis (Weibull) draws a capability histogram of the individual

measurements overlaid with a Weibull curve based on the process shape and scale.
This graph helps you make a visual assessment of the assumption that your data
follow a Weibull distribution. The report also includes a table of overall process
capability statistics.
Capability Sixpack (Normal) combines the following charts into a single display,
along with a subset of the capability statistics:
an X (or Individuals), R or S (or Moving Range), and run chart, which can be used
to verify that the process is in a state of control
a capability histogram and normal probability plot, which can be used to verify
that the data are normally distributed
a capability plot, which displays the process variability compared to the
specifications
CONTENTS
14-3
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
Chapter 14
HOW TO USE
Capability Sixpack (Between/Within) is appropriate for subgroup data in which

there is a strong between-subgroup source of variation. Capability Sixpack (Between/
Within) combines the following charts into a single display, along with a subset of the
capability statistics:
an Individuals Chart, Moving Range Chart, and R Chart or S Chart, which can be
used to verify that the process is in a state of control
a capability histogram and normal probability plot, which can be used to verify
that the data are normally distributed
a capability plot, which displays the process variability compared to specifications
Capability Sixpack (Weibull) combines the following charts into a single display,
along with a subset of the capability statistics:
an X (or Individuals), R (or Moving Range), and run chart, which can be used to
verify that the process is in a state of control
a capability histogram and Weibull probability plot, which can be used to verify
that the data come from a Weibull distribution
a capability plot, which displays the process variability compared to the
specifications
Although the Capability Sixpack commands give you fewer statistics than the Capability
Analysis commands, the array of charts can be used to verify that the process is in
control and that the data follow the chosen distribution.
Note
Capability statistics are simple to use, but they have distributional properties that are not
fully understood. In general, it is not good practice to rely on a single capability statistic
to characterize a process. See [2], [4], [5], [6], [9], [10], and [11] for a discussion.
Capability Analysis (Binomial) is appropriate when your data consists of the

number of defectives out of the total number of parts sampled. The report draws a P
chart, which helps you verify that the process is in a state of control. The report also
includes a chart of cumulative %defectives, histogram of %defectives, and defective
rate plot.
Capability Analysis (Poisson) is appropriate when your data take the form of the
number of defects per item. The report draws a U chart, which helps you to verify
that the process is in a state of control. The report also includes a chart of the
cumulative mean DPU (defects per unit), histogram of DPU, and a defect rate plot.
Capability statistics
Process capability statistics are numerical measures of process capabilitythat is, they
measure how capable a process is of meeting specifications. These statistics are simple
and unitless, so you can use them to compare the capability of different processes.
Capability statistics are basically a ratio between the allowable process spread (the
width of the specification limits) and the actual process spread (6). Some of the
statistics take into account the process mean or target.
14-4
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
Process capability command
Capability Analysis (Normal) and

Capability Sixpack (Normal)
Cp, Cpk, CPU, CPL, and Cpm (if you

specify a target)associated with
within variation
Pp, Ppk, PPU, PPLassociated with

overall variation
Cp, Cpk, CPU, CPL, and Cpm (if you

specify a target)associated with
within and between variation

overall variation

overall variation
Capability Analysis (Between/Within) and

Capability Sixpack (Between/Within)
Capability Analysis (Weibull) and

Capability Sixpack (Weibull)
For more information, see Capability statistics on page 14-9, Capability statistics on page
14-21, and Capability statistics on page 14-26.
Many practitioners consider 1.33 to be a minimum acceptable value for the process
capability statistics, and few believe that a value less than 1 is acceptable. A value less
than 1 indicates that your process variation is wider than the specification tolerance.
Here are some guidelines for how the statistics are used:
This statistic
is used when
Definition
Cp or Pp
the process is centered

between the specification
limits
ratio of the tolerance (the width of the

specification limits) to the actual spread
(the process tolerance):
(USL LSL) / 6
Cpk or Ppk
the process is not

centered between the
specification limits, but
falls on or between them
ratio of the tolerance (the width of the

specification limits) to the actual spread,
taking into account the process mean
relative to the midpoint between
specifications:
minimum [(USL ) / 3, ( LSL) / 3]
Note
CPU or PPU
the process only has an

upper specification limit
USL - / 3
CPL or PPL
the process only has a

lower specification limit
- LSL / 3
If the process target is not the midpoint between specifications, you may prefer to use
Cpm in place of Cpk, since Cpm measures process mean relative to the target rather than
the midpoint between specifications. See [9] for a discussion. You can calculate Cpm by
entering a target in the Options subdialog box.
CONTENTS
14-5
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE
Capability Analysis (Normal Distribution)
Non-normal data
When you have non-normal data, you can either transfom the data in such a way that
the normal distribution is a more appropriate model, or choose a Weibull probability
model for the data.
To transform the data, use Capability Analysis (Normal), Capability Sixpack (Normal),
Capability Analysis (Between/Within), or Capability Sixpack (Between/Within) with
the optional Box-Cox power transformation. See Box-Cox Transformation for
Non-Normal Data on page 12-6.
To use a Weibull probability model, use Capability Analysis (Weibull) and Capability
Sixpack (Weibull).
This table summarizes the differences between the methods.

Normal model with Box-Cox transformation
Weibull model
Uses transformed data for the histogram,

specification limits, target, process parameters
(mean, within and overall standard deviations), and
capability statistics
Uses actual data units for the histogram,

process parameters (shape and scale),
and capability statistics
Calculates both within and overall process

parameters and capability statistics
Calculates only overall process

parameters and capability statistics
Draws a normal curve over the histogram to help

you determine whether the transformation made
the data more normal
Draws a Weibull curve over the histogram

to help you determine whether the data
fit the Weibull distribution
Which method is better? The only way to answer that question is to see which model
fits the data better. If both models fit the data about the same, it is probably better to
choose the normal model, since it provides estimates of both overall and within process
capability.

Use Capability Analysis (Normal) to produce a process capability report when your data
are from a normal distribution or when you have Box-Cox transformed data. The report
includes a capability histogram overlaid with two normal curves, and a complete table
of overall and within capability statistics. The two normal curves are generated using
the process mean and within standard deviation and the process mean and overall
standard deviation.
The report also includes statistics of the process data, such as the process mean, the
target (if you enter one), the within and overall standard deviation, and the process
specifications; the observed performance; and the expected within and overall
14-6
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
performance. The report can be used to visually assess whether the data are normally
distributed, whether the process is centered on the target, and whether it is capable of
consistently meeting the process specifications.
A model which assumes the data are from a normal distribution suits most process data.
If your data are very skewed, see the discussion under Non-normal data on page 14-6.
Data
You can use individual observations or data in subgroups. Individual observations
should be structured in one column. Subgroup data can be structured in one column,
or in rows across several columns. When you have subgroups of unequal size, enter the
data in a single column, then set up a second column of subgroup indicators. For
examples, see Data on page 12-3.
If you have data in subgroups, you must have two or more observations in at least one
subgroup in order to estimate the process standard deviation.
To use the Box-Cox transformation, data must be positive.
If an observation is missing, MINITAB omits it from the calculations.
h To perform a capability analysis (normal probability model)
1 Choose Stat Quality Tools Capability Analysis (Normal).
2 Do one of the following:
When subgroups or individual observations are in one column, enter the data
column in Single column. In Subgroup size, enter a subgroup size or column of
subgroup indicators. For individual observations, enter a subgroup size of 1.
When subgroups are in rows, choose Subgroups across rows of, and enter the
columns containing the rows in the box.
3 In Lower spec or Upper spec, enter a lower and/or upper specification limit,
respectively. You must enter at least one of them.

4 If you like, use any of the options listed below, then click OK.
CONTENTS
14-7
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE
Options
Capability Analysis (Normal) dialog box
Note
define the upper and lower specification limits as boundaries, meaning

measurements cannot fall outside those limits. As a result, the expected % out of
spec is set to 0 for boundaries. If you choose boundaries, then USL (upper
specification limits) and LSL (lower specification limit) will be replaced by UB (upper
boundary) and LB (lower boundary) on the analysis.
When you define the upper and lower specification limits as boundaries, MINITAB still
calculates the observed % out-of-spec. If the observed % out-of-spec comes up nonzero,
this is an obvious indicator of incorrect data.
enter historical values for (the process mean) and (the process potential standard
deviation) if you have known process parameters or estimates from past data. If you
do not specify a value for or , MINITAB estimates them from the data.
Estimate subdialog box
estimate the process standard deviation () various wayssee Estimating the process
variation on page 14-10.
Options subdialog box
use the Box-Cox power transformation when you have very skewed datasee Use
the Box-Cox power transformation for non-normal data on page 12-68.
enter a process target, or nominal specification. MINITAB calculates Cpm in addition

to the standard capability statistics.
calculate the capability statistics using an interval other than six standard deviations
wide (three on either side of the process mean) by entering a sigma tolerance. For
example, entering 12 says to use an interval 12 standard deviations wide, six on
either side of the process mean.
perform only the within-subgroup analysis or only the overall analysis. The default is
to perform both.
display observed performance, expected within performance, and expected

overall performance in percents or parts per million. The default is parts per
million.
enter a minimum and/or maximum scale to appear on the capability histogram.
display benchmark Z scores instead of capability statistics. The default is to display

capability statistics.
display the capability analysis graph or not. The default is to display the graph.
replace the default graph title with your own title.
14-8
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
Storage subdialog box
store your choice of statistics in worksheet columns. The statistics available for
storage depend on the options you have chosen in the Capability Analysis (Normal)
dialog box and subdialog boxes.
When you use the normal distribution model for the capability analysis, MINITAB
calculates the capability statistics associated with within variation (Cp, Cpk, CPU, and
CPL) and with overall variation (Pp, Ppk PPU, PPL). To interpret these statistics, see
Capability statistics on page 14-4.
Cp, Cpk, CPU, and CPL represents the potential capability of your processwhat your
process would be capable of if the process did not have shifts and drifts in the subgroup
means. To calculate these, Minitab estimates within considering the variation within
subgroups, but not the shift and drift between subgroups.
Note
When your subgroup size is one, the within variation estimate is based on a moving
range, so that adjacent observations are effectively treated as subgroups.
Pp, Ppk, PPU, and PPL represent the overall capability of the process. When calculating
these statistics, MINITAB estimates overall considering the variation for the whole study.
Each small curve
represents within (or
potential) variation, or
variation for one
subgroup (one
moment in time).
The large curve
represents overall
variationthe
variation for the
whole study.
Overall capability depicts how the process is actually performing relative to the
specification limits. Within capability depicts how the process could perform relative to
the specification limits, if shifts and drifts could be eliminated. A substantial difference
between overall and within variation may indicate that the process is out of control, or it
may indicate sources of variation not estimated by within capability.
CONTENTS
14-9
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE
Estimating the process variation

An important step in a capability analysis with normal data is estimating the process
variation using the standard deviation, sigma (). Both Capability Analysis (Normal) and
Capability Sixpack (Normal) calculate within (within-subgroup) and overall variation.
The capability statistics associated with the within variation are Cp, Cpk, CPU, and CPL.
The statistics associated with the overall variation are Pp, Ppk, PPU, and PPL.
To calculate overall, MINITAB uses the standard deviation of all of the data.
To calculate within, MINITAB provides several options, which are listed below. For a
discussion of the relative merits of these methods, see [1].
h To specify a method for estimating within
1 In the Capability Analysis (Normal) or Capability Sixpack (Normal) main dialog box,
click Estimate.
For subgroup sizes greater than one, to base the estimate on:
the average of the subgroup rangeschoose Rbar.
the average of the subgroup standard deviationschoose Sbar. To not use an
unbiasing constant in the estimation, uncheck Use unbiasing constants.
the pooled standard deviation (the default)choose Pooled standard
deviation. To not use an unbiasing constant in the estimation, uncheck Use
unbiasing constants.
For individual observations (subgroup size is one), to base the estimate on:
the average of the moving range (the default)choose Average moving
range. To change the length of the moving range from 2, check Use moving
range of length and enter a number in the box.
the median of the moving rangechoose Median moving range. To change
the length of the moving range from 2, check Use moving range of length
and enter a number in the box.
the square root of MSSD (mean of the squared successive differences)choose
Square root of MSSD. To not use an unbiasing constant in the estimation,
uncheck Use unbiasing constants.
14-10
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
3 Click OK.
e Example of a capability analysis (normal probability model)
Suppose you work at an automobile manufacturer in a department that assembles

engines. One of the parts, a camshaft, must be 600 mm +2 mm long to meet
engineering specifications. There has been a chronic problem with camshaft lengths
being out of specificationa problem which has caused poor-fitting assemblies down
the production line and high scrap and rework rates.
Upon examination of the inventory records, you discovered that there were two
suppliers for the camshafts. An X and R chart showed you that Supplier 2s camshaft
production was out of control, so you decided to stop accepting production runs from
them until they get their production under control.
After dropping Supplier 2, the number of poor quality assemblies has dropped
significantly, but the problems have not completely disappeared. You decide to run a
capability study to see whether Supplier 1 alone is capable of meeting your engineering
specifications.
1 Open the worksheet CAMSHAFT.MTW.
3 In Single column, enter Supp1. In Subgroup size, enter 5.
4 In Lower spec, enter 598. In Upper spec, enter 602.
5 Click Options. In Target (adds Cpm to table), enter 600. Click OK in each dialog
box.
Graph
window
output
CONTENTS
14-11
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE
Interpreting the results

If you want to interpret the process capability statistics, your data should approximately
follow a normal distribution. This requirement appears to have been fulfilled, as shown
by the histogram overlaid with a normal curve.
But you can see that the process mean (599.55) falls short of the target (600). And the
left tail of the distribution falls outside the lower specification limits. This means you will
sometimes see camshafts that do not meet the lower specification of 598 mm.
The Cpk index indicates whether the process will produce units within the tolerance
limits. The Cpk index for Supplier 1 is only 0.90, indicating that they need to improve
their process by reducing variability and centering the process around the target.
Likewise, the PPM < LSLthe number of parts per million whose characteristic of
interest is less than the lower specis 3621.06. This means that approximately 3621
out of a million camshafts do not meet the lower specification of 598 mm.
Since Supplier 1 is currently your best supplier, you will work with them to improve their
process, and therefore, your own.
e Example of a capability analysis with a Box-Cox transformation
Suppose you work for a company that manufactures floor tiles and are concerned about
warping in the tiles. To ensure production quality, you measure warping in ten tiles each
working day for ten days.
A histogram shows that your data do not follow a normal distribution, so you decide to
use the Box-Cox power transformation to try to make the data more normal.
First you need to find the optimal lambda () value for the transformation. Then you will
do the capability analysis, performing the Box-Cox transformation with that value.
1 Open the worksheet TILES.MTW.
2 Choose Stat Control Charts Box-Cox Transformation.
3 In Single column, enter Warping. In Subgroup size, type 10. Click OK.
14-12
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
Graph
window
output
The best estimate of lambda is 0.449, but practically speaking, you may want a lambda
value that corresponds to an intuitive transformation, such as the square root (a lambda
of 0.5). In our example, 0.5 is a reasonable choice because it falls within the 95%
confidence interval, as marked by vertical lines on the graph. So you will run the
Capability Analysis with a Box-Cox transformation, using = 0.5.
2 In Single column, enter Warping. In Subgroup size, enter 10.
3 In Upper spec, enter 8.
4 Click Options.
5 Check Box-Cox power transformation (W = Y**Lambda). Choose Lambda = 0.5
(square root). Click OK in each dialog box.

Graph
window
output
CONTENTS
14-13
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE
Capability Analysis (Between/Within)

As you can see from the normal curve overlaying the histogram, the Box-Cox
transformation normalized the data. Now the process capability statistics are
appropriate for this data.
Because you only entered an upper specification limit, the capability statistics printed
are CPU and Cpk. Both statistics are 0.76, below the guideline of 1.33, so your process
does not appear to be capable. You can also see on the histogram that some of the
process data fall beyond the upper spec limit.
You decide to perform a capability analysis with this data using a Weibull model, to see
how the fit comparessee Example of a capability analysis (Weibull probability model) on
page 14-22.

Use Capability Analysis (Between/Within) to produce a process capability report using
both between-subgroup and within-subgroup variation. When you collect data in
subgroups, random error within subgroups may not be the only source of variation to
consider. There may also be random error between subgroups. Under these conditions,
the overall process variation is due to both the between-subgroup variation and the
within-subgroup variation.
Capability Analysis (Between/Within) computes standard deviations within subgroups
and between subgroups, or you may specify historical standard deviations. These will be
combined (pooled) to compute the total standard deviation. The total standard
deviation will be used to calculate the capability statistics, such as Cp and Cpk.
The report includes a capability histogram overlaid with two normal curves, and a
complete table of overall and total (between and within) capability statistics. The
normal curves are generated using the process mean and overall standard deviation and
the process mean and total standard deviation.
The report also includes statistics of the process data, such as the process mean, target,
if you enter one, total (between and within) and overall standard deviation, and
observed and expected performance.
Data
You can use data in subgroups, with two or more observations. Subgroup data can be
structured in one column, or in rows across several columns.
Ideally, all subgroups should be the same size. If your subgroups are not all the same
size, due to missing data or unequal subgroup sizes, only subgroups of the majority size
are used for estimating the between-subgroup variation.
14-14
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
h To perform a capability analysis (between/within)

1 Choose Stat Quality Tools Capability Analysis (Between/Within).
When subgroups are in one column, enter the data column in Single column. In
Subgroup size, enter a subgroup size or column of subgroup indicators.

Options
Capability Analysis (Between/Within) dialog box
Note
define the upper and lower specification limits as boundaries, meaning

measurements cannot fall outside those limits. As a result, the expected % out of
spec is set to 0 for a boundary. If you choose a boundary, MINITAB does not calculate
capability statistics for that side.
When you define the upper and lower specification limits as boundaries, MINITAB still
enter historical values for (the process mean) and within subgroups and/or
between subgroups if you have known process parameters or estimates from past
data. If you do not specify a value for or , MINITAB estimates them from the data.
CONTENTS
14-15
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE
estimate the within and between standard deviations () various wayssee

Estimating the process variation on page 14-17.
enter a process target, or nominal specifications. MINITAB calculates Cpm in addition

perform the between/within subgroup analysis only, or the overall analysis only. The
default is to perform both.
display observed performance, expected between/within performance, and

expected overall performance in percents or parts per million. The default is parts
per million.
display the capability analysis graph or not. The default is to display the graph.
enter a minimum and/or maximum scale to appear on the capability histogram.
Storage subdialog box
store your choice of statistics in worksheet columns. The statistics available for
storage depend on the options you have chosen in the Capability Analysis (Between/
Within) dialog box and subdialog boxes.
When you use Capability Analysis (Between/Within), MINITAB calculates both overall
capability statistics (Pp, Ppk, PPU, and PPL) and between/within capability statistics (Cp,
Cpk, CPU, and CPL). To interpret these statistics, see Capability statistics on page 14-4.
means. To calculate these, Minitab estimates within and between and pools them to
estimate total. Then, total is used to calculate the capability statistics.
14-16
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
Estimating the process variation

An important step in a capability analysis with normal data is estimating the process
variation using the standard deviation, sigma (). Both Capability Analysis (Between/
Within) and Capability Sixpack (Between/Within) calculate within, between, total
(between/within), and overall variation. The capability statistics associated with total
variation are Cp, Cpk, CPU, and CPL. The statistics associated with overall variation are
Pp, Ppk, PPU, and PPL.
To calculate overall, MINITAB uses the standard deviation of all of the data.
To calculate within and between, MINITAB provides several options, which are listed
below. For a discussion of the relative merits of these methods, see [1].
To calculate total, MINITAB pools within and between.
For the formulas used to estimate the process standard deviations (), see Help.
h To specify methods for estimating within and between
1 In the Capability Analysis (Between/Within) or Capability Sixpack (Between/Within)
main dialog box, click Estimate.
2 To change the method for estimating within, choose one of the following:
the average of the subgroup rangeschoose Rbar.
the average of the subgroup standard deviationschoose Sbar. To not use an

unbiasing constant in the estimation, uncheck Use unbiasing constants.
the pooled standard deviation (the default)choose Pooled standard deviation.

To not use an unbiasing constant in the estimation, uncheck Use unbiasing
constants.
3 To change the method for estimating between, choose one of the following:
the average of the moving range (the default)choose Average moving range.
To change the length of the moving range from 2, check Use moving range of
length and enter a number in the box.
CONTENTS
14-17
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE
the median of the moving rangechoose Median moving range. To change the
length of the moving range from 2, check Use moving range of length and enter
a number in the box.
the square root of MSSD (mean of the squared successive differences)choose

Square root of MSSD. To not use an unbiasing constant in the estimation,
uncheck Use unbiasing constants.
4 Click OK.
e Example of a capability analysis (between/within)
Suppose you are interested in the capability of a process that coats rolls of paper with a
thin film. You are concerned that the paper is being coated with the correct thickness of
film and that the coating is applied evenly throughout the roll. You take three samples
from 25 consecutive rolls and measure coating thickness. The thickness must be 50 3
to meet engineering specifications.
1 Open the worksheet BWCAPA.MTW.
2 Choose Stat Quality Tools Capability Analysis (Between/Within).
3 In Single column, enter Coating. In Subgroup size, enter Roll.
4 In Lower spec, enter 47. In Upper spec, enter 53. Click OK.
Graph
window
output
Interpreting results
You can see that the process mean (49.8829) falls close to the target of 50. The Cpk
index indicates whether the process will produce units within the tolerance limits. The
Cpk index is only 1.21, indicating that the process is fairly capable, but could be
improved.
The PPM Total for Expected Between/Within Performance is 193.94. This means that
approximately 194 out of a million coatings will not meet the specification limits. This
analysis tells you that your process is fairly capable.
14-18
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Capability Analysis (Weibull Distribution)
Process Capability

Use the Capability Analysis (Weibull) command to produce a process capability report
when your data are from a Weibull distribution. The report includes a capability
histogram overlaid with a Weibull curve and a table of overall capability statistics. The
Weibull curve is generated from the process shape and scale.
The report also includes statistics of the process data, such as the mean, shape, scale,
target (if you enter one), and process specifications; the actual overall capability; and
the observed and expected overall performance. The report can be used to visually
assess the distribution of the process relative to the target, whether the data follow a
Weibull distribution, and whether the process is capable of meeting the specifications
consistently.
When using the Weibull model, MINITAB calculates the overall capability statistics, Pp,
Ppk, PPU, and PPL. The calculations are based on maximum likelihood estimates of the
shape and scale parameters for the Weibull distribution, rather than mean and variance
estimates as in the normal case. If you have data that do not follow a normal
distribution, and you want to calculate the within capability statistics, Cp and Cpk, use
Capability Analysis (Normal Distribution) on page 14-6 with the optional Box-Cox power
transformation. For a comparison of the methods used for non-normal data, see
Non-normal data on page 14-6.
Data
You can enter your data in a single column or in multiple columns if you have arranged
subgroups across rows. Because the Weibull capability analysis does not calculate within
capability statistics, MINITAB does not used subgroups in calculations. For examples, see
Data on page 12-3.
Data must be positive.
If an observation is missing, MINITAB omits it from the calculations.
CONTENTS
14-19
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE

h To perform a capability analysis (Weibull probability model)
1 Choose Stat Quality Tools Capability Analysis (Weibull).
When subgroups or individual observations are in one column, choose Single

column and enter the column containing the data.
respectively. You must enter at least one of them. These limits must be positive
numbers, though the lower spec can be 0.
Options
Capability Analysis (Weibull) dialog box
Note
define the upper and lower specification limits as boundaries, meaning that it is
impossible for a measurement to fall outside that limit. As a result, when calculating
the expected % out-of-spec, MINITAB sets this value to 0 for a boundary.
When you define the upper or lower specification limits as boundaries, MINITAB still
14-20
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
enter historical values for the Weibull shape and scale parameterssee Weibull family
of distributions on page 14-21.
enter a process target or nominal specification. MINITAB calculates Cpm in addition to

the standard capability statistics.
When you use the Weibull model for the capability analysis, MINITAB only calculates the
overall capability statistics, Pp, Ppk, PPU, and PPL. The calculations are based on
maximum likelihood estimates of the shape and scale parameters for the Weibull
distribution, rather than mean and variance estimates as in the normal case.
To interpret these statistics, see Capability statistics on page 14-4.
Weibull family of distributions

The Weibull distribution is actually a family of distributions, including such distributions
as the exponential and Rayleigh. Its defining parameters are the shape () and scale ().
The appearance of the distribution varies widely, depending on the size of . A = 1, for
instance, gives an exponential distribution; a = 2 gives a Rayleigh distribution.
If you like, you can enter historical values for the shape and scale. If you do not enter
historical values, MINITAB obtains maximum likelihood estimates from the data.
Caution
Because the shape and scale parameters define the properties of the Weibull distribution,
they also define the probabilities used to calculate the capability statistics. If you enter
known values for the parameters, keep in mind that small changes in the parameters,
especially the shape, can have large effects on the associated probabilities.
CONTENTS
14-21
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE

h To enter historical values for the shape and scale parameters
1 In the Capability Analysis (Weibull) or Capability Sixpack (Weibull) main dialog box,
click Options.
2 Under Shape parameter, choose one of the following:
1 (Exponential)
2 (Rayleigh)
Historical value, and enter a positive value in the box
3 In Scale parameter, choose Historical value, and enter a positive value for the scale.
Click OK.
e Example of a capability analysis (Weibull probability model)
Suppose you work for a company that manufactures floor tiles, and are concerned
about warping in the tiles. To ensure production quality, you measured warping in ten
tiles each working day for ten days.
A histogram of the data showed that it did not come from a normal distributionsee
Example of a capability analysis with a Box-Cox transformation on page 14-12. So you
decide to perform a capability analysis based on a Weibull probability model.
2 Choose Stat Quality Tools Capability Analysis (Weibull).
3 In Single column, enter Warping.
4 In Upper spec, type 8. Click OK.
14-22
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
Graph
window
output

The capability histogram does not show evidence of any serious discrepancies between
the assumed model and the data.
But you can see that the right tail of the distribution falls over the upper specification
limit. This means you will sometimes see warping higher than the upper specification of
8 mm.
The Ppk and PPU indices tell you whether the process will produce tiles within the
tolerance limits. Both indices are 0.77, below the guideline of 1.33. Thus, your process
does not appear to be capable.
Likewise, the PPM > USLthe number of parts per million above the upper specis
20000.00. This means that 20,000 out of a million tiles will warp more than the upper
specification of 8 mm.
To see the same data analyzed with Capability Analysis (Normal), see Example of a
capability analysis with a Box-Cox transformation on page 14-12.
CONTENTS
14-23
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE
Capability Sixpack (Normal Distribution)

Use the Capability Sixpack (Normal) command to assess process capability in a glance
when your data are from the normal distribution or you have Box-Cox transformed
data. Capability Sixpack combines the following information into a single display:
an X chart (or Individuals chart for individual observations)
an R chart or S chart (or MR chart for individual observations)
a run chart of the last 25 subgroups (or last 25 observations)
a histogram of the process data
a normal probability plot
a process capability plot
within and overall capability statistics: Cp, Cpk, Cpm (if you enter a target), and
within; Pp, Ppk, and overall
The X , R, and run charts can be used to verify that the process is in a state of control.
The histogram and normal probability plot can be used to verify that the data are
normally distributed. Lastly, the capability plot gives a graphical view of the process
variability compared to the specifications. Combined with the capability statistics, this
information can help you assess whether your process is in control and the product
meets specifications.
A model that assumes the data are from a normal distribution suits most process data. If
your data are either very skewed or the within-subgroup variation is not constant (for
example, when this variation is proportional to the mean), see the discussion under
Data
You can enter individual observations or data in subgroups. Individual observations
should be structured in one column. Subgroup data can be structured in one column,
or in rows across several columns. When you have subgroups of unequal size, enter the
subgroups in a single column, then set up a second column of subgroup indicators. For
If you have data in subgroups, you must have two or more observations in at least one
subgroup in order to estimate the process standard deviation. Subgroups need not be
the same size.
If a single observation in the subgroup is missing, MINITAB omits it from the calculations
of the statistics for that subgroup. Such an omission may cause the control chart limits
and the center line to have different values for that subgroup. If an entire subgroup is
missing, there is a gap in the chart where the statistic for that subgroup would have
been plotted.
14-24
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
h To make a capability sixpack (normal probability model)

1 Choose Stat Quality Tools Capability Sixpack (Normal).

Options
Capability Sixpack (Normal) dialog box
enter your own value for (the process mean) and (the process potential standard
deviation) if you have known process parameters or estimates from past data. If you
do not specify a value for or , MINITAB estimates them from the data.
Tests subdialog box
do your choice of eight tests for special causessee Do tests for special causes on
page 12-64. To adjust the sensitivity of the tests, use Defining Tests for Special Causes
on page 12-5.
CONTENTS
14-25
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE

variation on page 14-10. The default estimate of is based on a pooled standard
deviation.
Note
When you estimate using the average of subgroup ranges (Rbar), MINITAB displays
an R chart.
When you estimate using the average of subgroup standard deviations (Sbar),
MINITAB displays an S chart.
When you estimate using the pooled standard deviation and your subgroup size is
less than ten, MINITAB displays an R chart.
ten or greater, MINITAB displays an S chart.
change the number of subgroups or observations to display in the run chart. The
default is 25.
enter the process target or nominal specification. MINITAB calculates Cpm in addition
Capability Sixpack (Normal) displays both the within and overall capability statistics,
Cp, Cpk, Cpm (if you specify a target), and within, and Pp, Ppk, and overall. To
interpret these statistics, see Capability statistics on page 14-4.
means. To calculate these, Minitab estimates within considering the variation within
subgroups, but not the shift and drift between subgroups.
14-26
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
e Example of a capability sixpack (normal probability model)
Suppose you work at an automobile manufacturer in a department that assembles

engines. One of the parts, a camshaft, must be 600 mm 2 mm long to meet
engineering specifications. There has been a chronic problem with camshaft lengths
being out of specificationa problem which has caused poor-fitting assemblies down
the production line and high scrap and rework rates.
Upon examination of the inventory records, you discovered that there were two
suppliers for the camshafts. An X and R chart showed you that Supplier 2s camshaft
production was out of control, so you decided to stop accepting production runs from
them until they get their production under control.
After dropping Supplier 2, the number of poor quality assemblies have dropped
significantly, but the problems have not completely disappeared. You decide to run a
capability sixpack to see whether Supplier 1 alone is capable of meeting your
engineering specifications.
1 Open the worksheet CAMSHAFT.MTW.
3 In Single column, enter Supp1. In Subgroup size, enter 5.
4 In Lower spec, enter 598. In Upper spec, enter 602. Click OK.
Graph
window
output

On both the X chart and the R chart, the points are randomly distributed between the
control limits, implying a stable process. It is also important to compare points on the R
chart with those on the X chart to see if the points follow each other. Yours do not,
again, implying a stable process.
CONTENTS
14-27
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE
The points on the run chart make a random horizontal scatter, with no trends or shifts
also indicating process stability.
If you want to interpret the process capability statistics, your data should approximately
follow a normal distribution. On the capability histogram, the data approximately
follow the normal curve. On the normal probability plot, the points approximately
follow a straight line. These patterns indicate that the data are normally distributed.
But from the capability plot, you can see that the process tolerance falls below the lower
specification limit. This means you will sometimes see camshafts that do not meet the
lower specification of 598 mm. Also, the values of Cp (1.16) and Cpk (0.90) are below
the guideline of 1.33, indicating that Supplier 1 needs to improve their process.
e Example of a capability sixpack with a Box-Cox tranformation
about warping in the tiles. To ensure production quality, you measure warping in ten
From previous analyses, you found that the tile data do not come from a normal
distribution, and that a Box-Cox transformation using a lambda value of 0.5 makes the
data more normal. For details, see Example of a capability analysis with a Box-Cox
transformation on page 14-12.
So you will run the capability sixpack using a Box-Cox transformation on the data.
3 In Single column, enter Warping. In Subgroup size, type 10.
4 In Upper spec, type 8.
5 Click Options.
6 Check Box-Cox power transformation (W = Y**Lambda). Choose Lambda = 0.5
(square root). Click OK in each dialog box.
14-28
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
Graph
window
output

On both the X chart and the R chart, the points are randomly distributed between the
control limits, implying a stable process. It is also important to compare points on the R
chart with those on the X chart for the same data to see if the points follow each other.
Yours do notagain, implying a stable process.
The points on the run chart make a random horizontal scatter, with no trends or shifts
also indicating process stability.
As you can see from the capability histogram, the data follow the normal curve. Also, on
the normal probability plot, the points approximately follow a straight line. These
patterns indicate that the Box-Cox transformation normalized the data. Now the
process capability statistics are appropriate for this data.
The capability plot, however, shows that the process is not meeting specifications. And
the values of Cpk (0.76) and Ppk (0.75) fall below the guideline of 1.33, so your process
does not appear to be capable.
CONTENTS
14-29
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE

Use the Capability Sixpack (Between/Within) command when you suspect that you may
have both between-subgroup and within-subgroup variation. Capability Sixpack
(Between/Within) allows you to assess process capability at a glance and combines the
following information into a single display:
an Individuals chart
a Moving Range chart
an R chart or S chart
a normal probability plot
between/within and overall capability statistics; Cp, Cpk, Cpm (if you specify a
target), within, between, and total; Pp, Ppk, and overall.
The Individuals, Moving Range, and R or S charts can verify whether or not the process
is in control. The histogram and normal probability plot can verify whether or not the
data are normally distributed. Lastly, the capability plot gives a graphical view of the
process variability compared to specifications. Combined with the capability statistics,
this information can help you assess whether your process is in control and the product
meets specifications.
A model that assumes that the data are from a normal distribution suits most process
data. If your data are either very skewed or the within subgroup variation is not
constant (for example, when the variation is proportional to the mean), see the
discussion under Non-normal data on page 14-6.
Data
You can enter data in subgroups, with two or more observations per subgroup.
Subgroup data can be structured in one column or in rows across several columns.
Ideally, all subgroups should be the same size. If your subgroups are not all the same
size, due to missing data or unequal sample sizes, only subgroups of the majority size
are used for estimating the between-subgroup variation. Control limits for the
Individuals and Moving Range charts are based on the majority subgroup size.
14-30
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
h To make a capability sixpack (between/within)

1 Choose Stat Quality Tools Capability Sixpack (Between/Within).
When subgroups are in one column, enter the data column in Single column. In
Subgroup size, enter a subgroup size or column of subgroup indicators.

Options
Capability Sixpack (Between/Within) dialog box
enter a historical value for (the process mean) and/or (within-subgroup and/or
between-subgroup standard deviations) if you have known process parameters or
estimates from past data. If you do not specify a value for or , MINITAB estimates
them from the data.
Tests subdialog box
do your choice of the eight tests for special causessee Do tests for special causes on
page 12-64. To adjust the sensitivity of the tests, use Defining Tests for Special Causes
on page 12-5.
CONTENTS
14-31
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE

variation on page 14-17.
Note
When you estimate using the average of subgroup ranges (Rbar), MINITAB displays
an R chart.
When you estimate using the average of subgroup standard deviations (Sbar),
MINITAB displays an S chart.
less than ten, MINITAB displays an R chart.
ten or greater, MINITAB displays an S chart.
use the Box-Cox power transformation when you have very skewed datasee
enter the process target or nominal specification. MINITAB calculates Cpm in addition
When you use Capability Analysis (Between/Within), MINITAB calculates both overall
capability statistics (Pp, Ppk, PPU, and PPL) and between/within capability statistics (Cp,
Cpk, CPU, and CPL). To interpret these statistics, see Capability statistics on page 14-4.
e Example of a capability sixpack (between/within)
Suppose you are interested in the capability of a process that coats rolls of paper with a
thin film. You are concerned that the paper is being coated with the correct thickness of
film and that the coating is applied evenly throughout the roll. You take three samples
from 25 consecutive rolls and measure coating thickness. The thickness must be 50 3
to meet engineering specifications.
Because you are interested in determining whether or not the coating is even
throughout a roll, you use MINITAB to conduct a Capability Sixpack (Between/Within).
1 Open the worksheet BWCAPA.MTW.
2 Select Stat Quality Tools Capability Sixpack (Between/Within).
14-32
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
3 In Single column, enter Coating. In Subgroup size, enter Roll.

4 In Lower spec, enter 47. In Upper spec, enter 53.
5 Click Tests. Choose Perform all eight tests. Click OK in each dialog box.
Graph
window
output
If you want to interpret the process capability statistics, your data need to come from a
normal distribution. This criteria appears to have been met. In the capability histogram,
the data approximately follow the normal curve. Also, on the normal probability plot,
the points approximately follow a straight line.
No points failed the eight tests for special causes, thereby implying that your process is
in control. The points on the Individuals and Moving Range chart do not appear to
follow each other, again indicating a stable process.
The capability plot shows that the process is meeting specifications. The values of Cpk
(1.21) and Ppk (1.14) fall just below the guideline of 1.33, so your process could use
some improvement.
CONTENTS
14-33
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE
Capability Sixpack (Weibull Distribution)

When a Weibull distribution is a good approximation of the distribution of your process
data, you can use the Capability Sixpack (Weibull) command to assess process
capability in a glance. Capability Sixpack (Weibull) combines the following information
into a single display:
an X chart (or I chart for individual observations)
an R chart (or MR chart for individual observations)
a run chart of the last 25 subgroups (or last 25 observations)
a Weibull probability plot
overall capability statistics Pp, Ppk, shape (), and scale ()
The X, R, and run charts can be used to verify that the process is in a state of control.
The histogram and Weibull probability plot can be used to verify that the data
approximate a Weibull distribution. Lastly, the capability plot gives a graphical view of
the process variability compared to the specifications. Combined with the capability
statistics, this information can help you assess whether your process is in control and
can produce output that consistently meets the specifications.
When using the Weibull model, MINITAB only calculates the overall capability statistics,
Pp and Ppk. The calculations are based on maximum likelihood estimates of the shape
and scale parameters for the Weibull distribution, rather than mean and variance
estimates as in the normal case. If you have data that do not follow a normal
distribution, and you want to calculate the within statistics (Cp, Cpk, within), see
Capability Analysis (Normal Distribution) on page 14-6 with the optional Box-Cox power
transformation. For a comparison of the methods used for non-normal data, see
Tip
To make a control chart that you can interpret properly, your data must follow a normal
distribution. If the Weibull distribution fits your data well, a lognormal distribution would
probably also provide a good fit. To transform your data, use the control chart command
with the optional Box-Cox transformation, entering Lambda = 0(natural log). For more
details, see Use the Box-Cox power transformation for non-normal data on page 12-68.
Data
You can enter individual observations or data in subgroups. Individual observations
should be structured in one column. Subgroup data can be structured in one column or
in rows across several columns. When you have subgroups of unequal size, enter the
subgroups in a single column, then set up a second column of subgroup indicators. For
14-34
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
Data must be positive.

If a single observation in the subgroup is missing, MINITAB omits it from the calculations
of the statistics for that subgroup. This may cause the control chart limits and the center
line to have different values for that subgroup. If an entire subgroup is missing, there is
a gap in the chart where the statistic for that subgroup would have been plotted.
h To make a capability sixpack (Weibull probability model)
1 Choose Stat Quality Tools Capability Sixpack (Weibull).
3 In Lower spec or Upper spec, enter a lower and/or upper specification limit. You
must enter at least one of them. These limits must be positive numbers, though the
lower spec can be 0.
Options
Caution
enter your own value for the Weibull shape and scale parameterssee Weibull family
of distributions on page 14-21. If you do not enter values, MINITAB obtains maximum
likelihood estimates from the data.
When you enter known values for the parameters, keep in mind that small changes in
the parameters, especially the shape, can have large effects on the associated
probabilities.
CONTENTS
14-35
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
Chapter 14
SC QREF
HOW TO USE
change the number of subgroups or observations to display in the run chart. The
default is 25.
Capability Sixpack (Weibull) displays the overall capability statistics, Pp and Ppk. These
calculations are based on maximum likelihood estimates of the shape and scale
parameters for the Weibull distribution, rather than mean and variance estimates as in
the normal case.
For information on interpreting these statistics, see Capability statistics on page 14-4.
e Example of a capability sixpack (Weibull probability model)
about warping in the tiles. To ensure production quality, you measured warping in ten
A histogram of the data revealed that it did not come from a normal distributionsee
Example of a capability analysis with a Box-Cox transformation on page 14-12. So you
decide to make a capability sixpack based on a Weibull probability model.
2 Choose Stat Quality Tools Capability Sixpack (Weibull).
3 In Single column, enter Warping. In Subgroup size, type 10.
4 In Upper spec, type 8. Click OK.
14-36
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
Capability Analysis (Binomial)
HOW TO USE
Process Capability
Graph
window
output

The capability histogram does not show evidence of any serious discrepancies between
the assumed model and the data. Also, on the Weibull probability plot, the points
approximately follow a straight line.
The capability plot, however, shows that the process is not meeting specifications. And
the value of Ppk (0.77) falls below the guideline of 1.33, so your process does not
appear to be capable.
To see the same data analyzed with Capability Sixpack (Normal), see Example of a
capability sixpack with a Box-Cox tranformation on page 14-28.

Use Capability Analysis (Binomial) to produce a process capability report when your
data are from a binomial distribution. Binomial distributions are usually associated with
recording the number of defective items out of the total number sampled.
For example, you might have a pass/fail gage that determines whether an item is
defective or not. You could then record the total number of parts inspected and the
number failed by the gage. Or, you could record the number of people who call in sick
on a particular day and the number of people scheduled to work each day.
CONTENTS
14-37
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
Chapter 14
HOW TO USE
Use Capability Analysis (Binomial) if your data meet the following conditions:
each item is the result of identical conditions
each item can result in one or two possible outcomes (success/failure, go/no-go)
the probability of a success (or failure) is constant for each item
the outcomes of the items are independent of each other
Capability Analysis (Binomial) produces a process capability report that includes the
following:
P chartverifies that the process is in a state of control
Chart of cumulative %defectiveverifies that you have collected data from enough
samples to have a stable estimate of %defective
Histogram of %defectivedisplays the overall distribution of the %defectives from

the samples collected
Defective rate plotverifies that the %defective is not influenced by the number of
items sampled
Data
Use data from a binomial distribution. Each entry in the worksheet column should
contain the number of defectives for a subgroup. When subgroup sizes are unequal,
you must also enter a corresponding column of subgroup sizes.
Suppose you have collected data on the number of parts inspected and the number of
parts that failed inspection. On any given data, both numbers may vary. Enter the
number that failed inspection in one column. If the total number inspected varies, enter
subgroup size in another column:
Failed Inspected
11
1003
12
968
9
897
13
1293
9
989
15
1423
Missing data
If an observation is missing, there is a gap in the P chart where that subgroup would
have been plotted. The other plots and charts simply exclude the missing observations.
14-38
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
Unequal subgroup sizes

In the P chart, the control limits are a function of the subgroup size. In general, the
control limits are further from the center line for smaller subgroups than they are for
larger ones. When you do have unequal subgroup sizes, the plot of %defective versus
sample size will permit you to verify that there is no relationship between the two. For
example, if you tend to have a smaller %defective when more items are sampled, this
could be caused by fatigued inspectors, a common problem. The subgroup size has no
bearing on the other charts because they only display the %defective.
h To perform a capability analysis (binomial probability model)
1 Choose Stat Quality Tools Capability Analysis (Binomial).
2 In Defectives, enter the column containing the number of defectives.

When your sample size is constant, enter the sample size value in Constant size.
When your sample sizes vary, enter the column containing sample sizes in Use
sizes in.
Options
Capability Analysis (binomial) dialog box
enter a historical value for the proportion of defectives. This value must be between 0
and 1.
enter a value for the % defective target.
CONTENTS
14-39
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
Chapter 14
HOW TO USE
Tests subdialog box
perform your choice of the four tests for special causessee Do tests for special causes
on page 13-15. To adjust the sensitivity of the tests, use Defining Tests for Special
Causes on page 12-5.
choose a color scheme for printing.
e Example of capability analysis (binomial probability model)
Suppose you are responsible for evaluating the responsiveness of your telephone sales
department, that is, how capable it is of answering incoming calls. You record the
number of calls that were not answered (a defective) by sales representatives due to
unavailability each day for 20 days. You also record the total number of incoming calls.
1 Open the worksheet BPCAPA.MTW.
2 Choose Stat Quality Tools Capability Analysis (Binomial).
3 In Defectives, enter Unavailable.
4 In Use sizes in, enter Calls. Click OK.
Graph
window
output
The P chart indicates that there is one point out of control. The chart of cumulative
%defect shows that the estimate of the overall defective rate appears to be settling
down around 22%, but more data may need to be collected to verify this. The rate of
defectives does not appear to be affected by sample size. The process Z is around 0.75,
which is very poor. This process could use a lot of improvement.
14-40
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Capability Analysis (Poisson)
Process Capability

Use Capability Analysis (Poisson) to produce a process capability report when your data
are from a Poisson distribution. Poisson data is usually associated with the number of
defects observed in an item, where the item occupies a specified amount of time or
specified space. The size of the item may vary, so you may also keep track of the size.
For example, if you manufacture electrical wiring, you may want to record the number
of breaks in a piece of wire. If the lengths of the wire vary, you will have to record the
size of each piece sampled. Or, if you manufacture appliances, you may want to record
the number of scratches on the surface of the appliance. Since the sizes of the surface
may be different, you may also record the size of each surface sampled, say in square
inches.
Use Capability Analysis (Poisson) when your data meet the following conditions:
the rate of defects per unit of space or time is the same for each item
the number of defects observed in the items are independent of each other
Capability Analysis (Poisson) produces a process capability report for data from a
Poisson distribution. The report includes the following:
U chartverifies that the process was in a state of control at the time the report was
generated
Chart of cumulative mean DPU (defects per unit)verifies that you have collected
data from enough samples to have a stable estimate of the mean
Histogram of DPUdisplays the overall distribution of the defects per unit from the
samples collected
Defect plot rateverifies that DPU is not influenced by the size of the items sampled
Data
Each entry in the worksheet column should contain the number of or defects for a
subgroup. When subgroup sizes are unequal, you must also enter a corresponding
column of subgroup sizes.
Suppose you have collected data on the number of defects per unit and the size of the
unit. For any given unit, both numbers may vary. Enter the number of defects in one
column. If the unit size varies, enter unit size in another column:
Failed Inspected
3
89
4
94
7
121
2
43
11
142
6
103
CONTENTS
14-41
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
Chapter 14
HOW TO USE
Missing data
If an observation is missing, there is a gap in the U chart where the subgroup would
have been plotted. The other plots and charts simply exclude the missing
observation(s).
Unequal subgroup sizes
In the U chart, the control limits are a function of the subgroup size. In general, the
control limits are further from the centerline for smaller subgroups than they are for
larger ones. When you do have unequal subgroup sizes, the plot of defects per unit
(DPU) versus sample size will permit you to verify that there is no relationship between
the two. For example, if you tend to have a smaller DPU when more items are sampled,
this could be caused by fatigued inspectors, a common problem. The subgroup size has
no bearing on the other charts, because they only display the DPU.
h To perform a capability analysis (Poisson distribution model)
1 Choose Stat Quality Tools Capability Analysis (Poisson).
2 In Defects, enter the column containing the number of defects.

When your unit size is constant, enter the unit size value in Constant size.
When your unit sizes vary, enter the column containing unit sizes in Use sizes in.
14-42
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
Process Capability
Options
Capability Analysis (Poisson) dialog box
enter historical values for (the process mean) if you have known process parameters
or estimates from past data. If you do not specify a value for , MINITAB estimates it
from the data.
enter a target DPU (defects per unit) for the process.
Tests subdialog box
perform the four tests for special causessee Do tests for special causes on page
13-15. To adjust the sensitivity of the tests, use Defining Tests for Special Causes on
page 12-5.
choose to use a full color, partial color, or black and white color scheme for printing.
e Example of capability analysis (Poisson probability distribution)
Suppose you work for a wire manufacturer and are concerned about the effectiveness of
the wire insulation process. You take random lengths of electrical wiring and test them
for weak spots in their insulation by subjecting them to a test voltage. You record the
number of weak spots and the length of each piece of wire (in feet).
1 Open the worksheet BPCAPA.MTW.
2 Choose Stat Quality Tools Capability Analysis (Poisson).
3 In Defects, enter Weak Spots.
4 In Uses sizes in, enter Lengths. Click OK.
CONTENTS
14-43
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
Chapter 14
HOW TO USE
References
Graph
window
output
The U Chart indicates that there are three points out of control. The chart of cumulative
mean DPU (defects per unit) has settled down around the value 0.0265, signifying that
enough samples were collected to have a good estimate of the mean DPU. The rate of
DPU does not appear to be affected by the lengths of the wire.
References
[1] L.K. Chan, S.W. Cheng, and F.A. Spiring (1988). A New Measure of Process
Capability: Cpm, Journal of Quality Technology, 20, July, pp.162175.
[2] Y. Chou, D. Owen, S. Borrego (1990). Lower Confidence Limits on Process
Capability Indices, Journal of Quality Technology, 22, July, pp.223229.
[3] Ford Motor Company (1983). Continuing Process Control and Process Capability
Improvement, Ford Motor Company, Dearborn, Michigan.
[4] L.A. Franklin and G.S. Wasserman (1992). Bootstrap Lower Confidence Limits for
Capability Indices, Journal of Quality Technology, 24, October, pp.196210.
[5] B. Gunter (1989). The Use and Abuse of Cpk, Part 2, Quality Progress, 22, March,
pp.108, 109.
[6] B. Gunter (1989). The Use and Abuse of Cpk, Part 3, Quality Progress, 22, May,
pp.79, 80.
14-44
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
References
HOW TO USE
Process Capability
[7] A.H. Jaehn (1989). How to Estimate Percentage of Product Failing Specifications,
Tappi,72, pp.227228.
[8] V.E. Kane (1986). Process Capability Indices, Journal of Quality Technology, 18, pp.
4152.
[9] R.H. Kushler and P. Hurley (1992). Confidence Bounds for Capability Indices,
Journal of Quality Technology, 24, October, pp.188195.
[10] W.L. Pearn, S. Kotz, and N.L. Johnson (1992). Distributional and Inferential
Properties of Process Capability Indices, Journal of Quality Technology, 24, October,
pp. 216231.
[11] R.N. Rodriguez (1992). Recent Developments in Process Capability Analysis,
Journal of Quality Technology, 24, October, pp.176187.
[12] T.P. Ryan (1989). Statistical Methods for Quality Improvement, John Wiley & Sons.
[13] L.P. Sullivan (1984). Reducing Variability: A New Approach to Quality, Quality
Progress, July, 1984, pp.15 21.
[14] H.M. Wadsworth, K.S. Stephens, and A.B. Godfrey (1986). Modern Methods for
Quality Control and Improvement, John Wiley & Sons.
[15] Western Electric (1956). Statistical Quality Control Handbook, Western Electric
Corporation, Indianapolis, Indiana.
CONTENTS
14-45
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
Chapter 14
HOW TO USE
References
14-46
CONTENTS
INDEX
MEET MTB
UGUIDE 1
UGUIDE 2
SC QREF
HOW TO USE

Process Capability Analysis in Minitab - Manual PDF

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Process Capability Analysis in Minitab - Manual PDF

Uploaded by

Copyright:

Available Formats

QCPRCAPA.

MK5 Page 1 Friday, December 17, 1999 12:52 PM

Process Capability Overview, 14-2

Capability Analysis (Normal Distribution), 14-6

Capability Analysis (Between/Within), 14-14

Capability Analysis (Weibull Distribution), 14-19

Capability Sixpack (Normal Distribution), 14-24

Capability Sixpack (Between/Within), 14-30

Capability Sixpack (Weibull Distribution), 14-34

Capability Analysis (Binomial), 14-37

Capability Analysis (Poisson), 14-41

MINITAB Users Guide 2

QCPRCAPA.MK5 Page 2 Friday, December 17, 1999 12:52 PM

Process Capability Overview

Choosing a capability command

normal or Weibull probability models (for measurement data)

normal data that might have a strong source of between-subgroup variation

binomial or Poisson probability models (for attributes or count data)

It is essential to choose the correct distribution when conducting a capability analysis.

MINITAB Users Guide 2

QCPRCAPA.MK5 Page 3 Friday, December 17, 1999 12:52 PM

Process Capability Overview

Box-Cox power transformation or a Weibull probability model. Non-normal data on

MINITABs capability commands

Capability Analysis (Normal) draws a capability histogram of the individual

Capability Analysis (Between/Within) draws a capability histogram of the

Capability Analysis (Weibull) draws a capability histogram of the individual

MINITAB Users Guide 2

QCPRCAPA.MK5 Page 4 Friday, December 17, 1999 12:52 PM

Capability Sixpack (Between/Within) is appropriate for subgroup data in which

Capability Analysis (Binomial) is appropriate when your data consists of the

MINITAB Users Guide 2

QCPRCAPA.MK5 Page 5 Friday, December 17, 1999 12:52 PM

Process Capability Overview

Process capability command

Capability Analysis (Normal) and

Cp, Cpk, CPU, CPL, and Cpm (if you

Pp, Ppk, PPU, PPLassociated with

Cp, Cpk, CPU, CPL, and Cpm (if you

Pp, Ppk, PPU, PPLassociated with

Pp, Ppk, PPU, PPLassociated with

Capability Analysis (Between/Within) and

Capability Analysis (Weibull) and

the process is centered

ratio of the tolerance (the width of the

the process is not

ratio of the tolerance (the width of the

the process only has an

the process only has a

MINITAB Users Guide 2

QCPRCAPA.MK5 Page 6 Friday, December 17, 1999 12:52 PM

Capability Analysis (Normal Distribution)

This table summarizes the differences between the methods.

Uses transformed data for the histogram,

Uses actual data units for the histogram,

Calculates both within and overall process

Calculates only overall process

Draws a normal curve over the histogram to help

Draws a Weibull curve over the histogram

Capability Analysis (Normal Distribution)

MINITAB Users Guide 2

QCPRCAPA.MK5 Page 7 Friday, December 17, 1999 12:52 PM

Capability Analysis (Normal Distribution)