Quick Guide To Six Sigma Statistics

The Quick Guide to Six Sigma
Statistics: 10 Tools Explained

Six Sigma is a proven quality improvement method that gets results. By
following a logical series of steps, organizations of all sizes have solved
remarkable problems and saved billions of dollars. Many practitioners
feel intimidated by the statistics vital to Six Sigma, but you dont need to
be. While data plays a critical role in improving quality, most of the analyses
used are not difficult to understand, even if youre not statistics-savvy.
Getting familiar with these tools is a good place to start. This guide
provides an overview of 10 statistical tools commonly used in Six Sigma,
and explains what they do and why theyre important.
1. Pareto Chart 2. Histogram
The Pareto Principle says that about 80% of A histogram provides a snapshot of
outcomes result from 20% of the causes. This numeric, continuous data. With histo-
likely even applies to your wardrobeperhaps grams, you can quickly identify the center
you wear 20% of your clothes 80% of the and spread of your data. Where does
time. The Pareto chart is a specialized type of most of the data fall? And where are the
bar chart that distinguishes the critical few minimum and maximum values, approxi-
causes from the trivial many so you can mately? A histogram also shows you if your
focus on whats most important. For example, data are bell-shaped or not, and can help
if you record defect types every time one you identify outliers, or highly unusual
occurs, a Pareto chart pinpoints the most data points, which may require further
frequent defects so you can direct improve- investigation.
ment efforts at the most prevalent problems.
www.minitab.com
3. Gage R&R numeric measurements, attribute agree-
ment analysis is ideal for categorical
assessments, such as Pass or Fail. This
tool will reveal whether or not people
rating these categories agree with
themselves, with other appraisers, and
with a known standard.
5. Process Capability
Would you weigh yourself using an unre-

liable scale? Would you wear a watch
that didnt keep time? You cant improve
a process that you cant adequately
measure, which is why we need Gage
R&R. This toolfor continuous numeric
measurements, such as weight, diameter,
and pressurehelps you determine if your
measurements are both repeatable and
reproducible, when the same person is Nearly every process has an acceptable
repeatedly measuring the same part, and lower and/or upper bound. Manufac-
when different operators are measuring tured parts cant be too large or too
the same part. small, wait times cant extend beyond
an acceptable threshold, fill weights
need to exceed a specified minimum.
4. Attribute Agreement Analysis Capability analysis quantifies how well
your process meets specifications, and
provides insight into how to improve a
poor process. Frequently cited capability
metrics include Cpk, Ppk, defects per
million opportunities (DPMO), and Sigma
level.
Attribute agreement analysis is another

tool for making sure you can trust your
data. Where Gage R&R is ideal for
www.minitab.com
6. t-Tests two means. For example, you can use
ANOVA to test if the average production
volumes across 3 shifts are equal. You
can also use ANOVA to analyze means
for more than 1 variable. For example,
you can simultaneously compare the
means for 3 shifts and the means for 2
manufacturing locations.
8. Regression
A t-test can be used to compare the

average of one sample to a target,
or to the average of another sample.
For example, if your company sells
beverages in 16 oz. containers, you
can use a 1-sample t-test to determine
if your production lines average fill is
off target. If you buy flavor syrup from
two suppliers and want to determine
if theres a difference in the average
volume of their respective shipments, Regression is useful for determining if
then you can use a 2-sample t-test to a relationship exists between an output
compare the two suppliers. and one or more input variables. For
example, you can determine if there
is a relationship between a companys
7. ANOVA marketing expenditures and its sales
revenue. If a relationship between the
variables does exist, then you can use
the regression equation to describe that
relationship and predict future output
values for given input values.
Where t-tests compare a mean to a

target, or two means to each other,
ANOVA lets you compare more than
www.minitab.com
9. DOE 10. Control Charts
While regression and ANOVA are A stable, and therefore predictable,

typically used for data thats already process is a hallmark of quality products
available, Design of Experiments (DOE) and services. Yet every process has natural
provides an efficient data collection fluctuation. A control chart distinguishes
strategy, where inputs are simultaneously special-cause variation from acceptable,
adjusted, to identify if relationships exist natural variation. These charts graph data
between inputs and outputs. Once you over time and flag out-of-control data
collect the data and identify the import- points so you can detect unusual variability
ant inputs, you can then use DOE to and take action only when necessary.
determine optimal settings. Control charts also help you ensure that
your process improvements are sustained
into the future.
Conclusion
Six Sigma projects can provide significant benefits for your business, but
you cannot reap those benefits without collecting and analyzing data so
you can understand where opportunities exist and make significant and
sustained improvements. The power to effect change and contribute to
the success of Six Sigma projects often lies in the hands of practitioners
who are highly skilled subject-matter experts in many fields, but not
statistics. With a basic understanding of the most commonly used Six
Sigma statistics, as seen here, and easy-to-use statistical software, you
can overcome the statistical hurdles associated with improving quality,
and analyze your data with confidence.
Michelle Paret, product marketing manager, Minitab Inc. [email protected]

Minitab is the leading provider of statistical software for quality improvement and statistics education.
More than 90% of Fortune 100 companies and more than 4,000 colleges and universities use Minitab 17,
our flagship product. Visit www.minitab.com to learn more or contact us at [email protected].
Minitab and the Minitab logo are all registered trademarks of Minitab, Inc., in the United
States and other countries. See minitab.com/legal/trademarks for more information.

Quick Guide To Six Sigma Statistics

Uploaded by

Copyright:

Available Formats

Quick Guide To Six Sigma Statistics

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

Quick Guide To Six Sigma Statistics

Uploaded by

Copyright:

Available Formats

The Quick Guide to Six Sigma

Statistics: 10 Tools Explained

1. Pareto Chart 2. Histogram

Would you weigh yourself using an unre-

Attribute agreement analysis is another

A t-test can be used to compare the

Where t-tests compare a mean to a

While regression and ANOVA are A stable, and therefore predictable,

Michelle Paret, product marketing manager, Minitab Inc. [email protected]

You might also like