Six Sigma Tools

Knowledge Center > Learn About Quality > Six Sigma > Tools

The Six Sigma expert uses qualitative and quantitative techniques to drive process improvement.
Although the tools, themselves, are not unique, the way they are applied and integrated as part of a
system is.

Six Sigma professionals do not always agree as to exactly which tools constitute the set. Some of the
statistical and graphical tools commonly used in improvement projects are listed below.

Defining a problem, improvement opportunity, or requirements:

Project charter to define the focus, scope, direction, and motivation for the improvement team

Voice of the customer to understand feedback from current and future customers indicating offerings
that satisfy, delight, and dissatisfy them

Value stream map to provide an overview of an entire process, starting and finishing at the customer,
and analyzing what is required to meet customer needs

Measuring process performance:

Process map for recording the activities performed as part of a process

Capability analysis to assess the ability of a process to meet specifications

Pareto chart to analyze the frequency of problems or causes

Analyzing processes to determine root causes of variation, defects, or poor performance:

Root cause analysis to uncover causes

Failure mode and effects analysis for identifying possible product, service, and process failures

Multi-vari chart to detect different types of variation within a process

Improving process performance by addressing root causes:

Design of experiments (DOE) to solve problems from complex processes or systems where there are
many factors influencing the outcome and where it is impossible to isolate one factor or variable from
the others

Kaizen event to introduce rapid change by focusing on a narrow project and using the ideas and
motivation of the people who do the work

Controlling the improved process and future performance:

Control plan to document what is needed to keep an improved process at its current level

Statistical process control (SPC) for monitoring process behavior

5S to create a workplace suited for visual control

Mistake proofing (poka-yoke) to make errors impossible or immediately detectable

Additionally, Six Sigma team leaders often use project management tools such as Gantt charts and team
engagement tools like brainstorming and nominal group technique.

More Perspectives on the Six Sigma Toolkit

Light Bulb Moment (open access)

Consider the define-measure-analyze-improve-control (DMAIC) roadmap and maximize quality tools

along the improvement journey.

A Webcast Overview of the Seven Lean Six Sigma Tools (ASQ members only)

The installments in this series provide an overview of seven common Lean Six Sigma tools: 5S system,
seven wastes, value stream mapping, kaizen, flow, visual workspace, and voice of the customer.
Which Control Chart Should You Use? (members only)

While control charts can be effective for evaluating performance and improvement in a Six Sigma
project, project managers should carefully evaluate different charts available to ensure the selection
provides the most useful information for the project.

Six Sigma Case Studies

Read case studies that feature details on the use of quality tools in the context of Six Sigma improvement
projects.

Lean Six Sigma and its tools have created an impact in the operations of many companies. Lean
and Six Sigma tools can be utilized to promote improvements in quality both as a systematic and
strategic manner. Most of the taught Lean Six Sigma tools are quality techniques that are not
really new. What can be different is simply the application and integration of the tools.

Lean Six Sigma tools are included in its Define-Measure-Analyze-Improve-Control (DMAIC)

improvement project execution roadmap. This roadmaps execution is to create robust processes
that let businesses attain standards that are high and in control.

In Lean Six Sigma, data are subjected to analysis in order to better comprehend problems and
identify customer needs. The phases of Lean Six Sigma are to quantify possible defects and its
causes, along with the reduction of process waste.

I will now address five of the DMAIC tools used in this process improvement methodology:

The 5 Whys
The 5 Whys tool is employed in order to move past the symptoms toward assimilating the actual
cause of a problem. By asking the question "Why" five times, a true cause can often be
determined.

A great number of organizations rely on the 5 Whys method for many reasons, including it is
simple, easy to accomplish, and does not require statistical analysis. The 5 Whys method is ideal
when the problem source is from human interactions and/or other quantifiable factors. To apply
this methodology, the following steps can be followed:

Document and elaborate on the problem.

Question why the problem occurred and come up with possible answers.

If answers to this question does not lead to a root cause, ask again Why and again document
responses.

Repeat the process again and again until the root cause has been determined.

Note, you may ask the question "Why" more or less than five times.

Fishbone Diagram

The fishbone diagram is also known as a "cause and effect diagram." A fishbone diagram is a
structured tool for brainstorming. This cause-and-effect diagram methodology is crafted to aid
organizational teams identify potential causes for a described issue. Some people refer to this
tool as Ishikawa diagram, named after its developer. The name fishbone originates from the
diagrams fishbone appearance.

With a fishbone brainstorming approach, the session is conducted around categories of causes
such as Methods, People, Machines, Equipment, Materials, Environment and Management. To
start the process, the team should state the problem. This statement is then followed by
brainstorming for root causes to the issue around the chosen categories.

After the team concurs on the problem statement, the question is placed at the head of the
fishbone. The primary bones of the fish are composed of drawn lines connected to the statement
of the problem. Each of the main bones in the fish address one of the chosen brainstorming
categories. Items from the brainstorming session will be documented as lines connected to these
main bones.

Histogram

The histogram is a data-containing graph which addresses the shape, frequency, dispersion and
other factors of a measurement. This tool can deliver a visual representation of data, which can
be hard to comprehend in other forms of presentations such as a spreadsheet or tabular format.
The histogram can be used to gain understand as to how a process response relates to customer
expectations; e.g., existing specifications or targeted objectives such as on-time delivery. This
tool can also help address the question of whether the process in use can actually provide a
desirable response so that customer requirements can consistently be met.

One advantage of histogram is that this visual presentation or summary can often be understood
even with a glance.

Regression Analysis

A regression analysis can be useful to determine that a process input has a relationship to the
output of a process. This knowledge can help identify an input to the process where control is
necessary to achieve a desired process-output response.

Possible issues when using regression analysis include:

Correlation does not imply causation.

Multicollinearity can cause havoc in an analysis and jeopardize the validity of its conclusions.
Multicollinearity occurs when in a regression model two or more of the predictors are
moderately or highly correlated.

A model might not be accurate because a few extreme data points can provide excess leverage
that distorts validity of the model.

The above considerations need to be taken into consideration when using regression analysis.

Run Chart/Time Series

A run chart is basically a graph displaying time series information, where the data are sequenced
from first to last. This tool can show trends and shifts. However, care needs to be exercised since
sometimes a trend may appear to be occurring but this apparent process shift may simply be the
result of common-cause variability; i.e., changes in a response because of not-unusual noise
variations from the process.

A 30,000-foot-level chart can often be used in lieu of a run chart to separate common-cause
variability from special cause and also make a statement of how the process is performing
relative to the needs of customers.

DMAIC Roadmap

As noted earlier, the above tools are just five of the many tools in the Lean Six Sigma tool kit.
These five Lean Six Sigma tools are integrated with other Lean Six Sigma techniques when
formulating the DMAIC roadmap. More information about the Lean Six Sigma process
improvement methodology and Lean Six Sigma tools integration is described in the article "Lean
Six Sigma DMAIC Process Improvement Roadmap."
HOW TO MEASURE DEFECT
RATE FOR SIX SIGMA

Related Book

SIX SIGMA FOR DUMMIES, 2ND EDITION

By Craig Gygi, Bruce Williams, Neil DeCarlo, Stephen R. Covey
The complementary measurement of yield for Six Sigma is defects. When a process or
characteristic doesnt perform within its specifications, it produces a noncompliant
condition, called a defect. If your yield is 90 percent, you naturally must have 10 percent
defects.

DEFECTS EQUAL FAILURE

When a process or characteristic doesnt perform within its specifications, it is
considered defective; in other words, it produces a noncompliant condition called a
defect.
Automatically defining a defect as a noncompliance with specifications may seem overly
simplified. Just because a characteristic exceeds a specification doesnt necessarily
mean that the system its part of will break or stop functioning.

DEFECTS PER UNIT

Six Sigma applies to all areas of business and productivity manufacturing, design,
sales, office administration, accounts receivable, healthcare, finance, and so on. Each
of these areas works on and produces different things products, services, processes,
environments, solutions, among others.
To bridge these diverse disciplines, in Six Sigma you call the thing youre working on a
unit. A unit may be a discretely manufactured product or an invoice that crosses your
desk. Whatever it is you do, in Six Sigma its called a unit.
A basic assessment of characteristic or process capability is to measure the total
number of defects that occur over a known number of units. You then transform this
measurement into a calculation of how often defects occur on a single unit, like this:

<img
src="http://d2r5da613aq50s.cloudfront.net/wp-content/uploads/357960.image0.jpg"
width="535" height="76" alt="image0.jpg"/>
where DPU stands for defects per unit.
For example, if you process 23 loan applications during a month and find 11 defects
misspelled names, missing prior residence information, incorrect loan amounts the
DPU for your loan application process is

<img
src="http://d2r5da613aq50s.cloudfront.net/wp-content/uploads/357961.image1.jpg"
width="286" height="66" alt="image1.jpg"/>
That means that for every two loans that leave your desk, you expect to see about one
defect.

DEFECTS PER OPPORTUNITY (DPO) AND

PER MILLION OPPORTUNITIES (DPMO)
A DPU of 0.478 for an automobile is viewed very differently than the same per-unit
defect rate on a bicycle. Thats because the automobile, with all its thousands of parts,
dimensions, and integrated systems, has many more opportunities for defects than the
bicycle has. A DPU of 0.478 on an automobile is evidence of a much lower defect rate
than the same DPU on a simpler product.
The key is in transforming the defect rate into terms that are common to any unit,
whatever it is or however complex it may be.

HOW TO DEAL WITH DPO

The way to level the playing field so you can directly compare the defect rates of
systems with very different complexities is to create a per-opportunity defect rate,
known as defects per opportunity (DPO). The common ground between any different
units is opportunity.
Examples of opportunities include the following:
 In a product, the critical dimension of diameter on an automobile axle
In a transactional process, the applicants mailing address on a loan approval
form
In a hospital, getting the correct medical history records into the patients file
In the design of a retail store environment, the placement of clearance sale racks
In a manufacturing process, the tightening of a bolt to the correct torque
The number of opportunities inherent to a unit, whatever that unit may be, is a direct
measure of its complexity. In fact, when you want to know how complex a unit is, you
count or estimate how many opportunities for success or failure exist. Sometimes,
opportunities are individual characteristics that are critical to the systems performance.
Other opportunities are characteristics that have a specification.
Use the following formula to calculate DPO:

<img
src="http://d2r5da613aq50s.cloudfront.net/wp-content/uploads/357962.image2.jpg"
width="535" height="60" alt="image2.jpg"/>
With a calculated DPO measurement, you can now fairly compare how capable an
automobile is to how capable a bicycle is. For example, you may observe 158 out-of-
specification characteristics on an automobile. After some study, you also determine
that the number of opportunities for success or failure within that automobile is 14,550.
Its DPO is then

<img
src="http://d2r5da613aq50s.cloudfront.net/wp-content/uploads/357963.image3.jpg"
width="347" height="74" alt="image3.jpg"/>
For a bicycle, on the other hand, you may find only two non-compliant characteristics
among its 173 critical characteristics. So its DPO is

<img
src="http://d2r5da613aq50s.cloudfront.net/wp-content/uploads/357964.image4.jpg"
width="300" height="67" alt="image4.jpg"/>
Even though an automobile and a bicycle are two very different items with very different
levels of complexity, the DPO calculations tell you that they both have about the same
real defect rate. But you observe more defects on the automobile, because that item
has many more opportunities for defects.

HOW TO ADDRESS LARGER AND

ACCUMULATED UNITS WITH DPMO
When the number of opportunities on a unit gets large and the number of observed
defects gets small, calculated DPO measurements become so small theyre hard to
work with. For example, two commercial airline crashes (defects) observed out of 6
million flights in a year translates into

<img
src="http://d2r5da613aq50s.cloudfront.net/wp-content/uploads/357965.image5.jpg"
width="515" height="72" alt="image5.jpg"/>
Although 0.000000333 is fortunate, its definitely an inconvenient number to work with!
Additionally, you may also want to estimate out into the future to know how many
defects will pile up after running the process or observing the characteristic for a long
time. After all, DPU and DPO look only at a single unit or a single opportunity.
A simple way to solve both of these problems is to count the number of defects over a
larger number of opportunities. For example, how many defects occur over a set of one
million opportunities? This defect rate measurement is called defects per million
opportunities and is used very frequently in Six Sigma. In fact, Six Sigma is famous for
its defect rate goal of 3.4 defects per million opportunities.
When a process is repeated over and over again many times like an automobile
assembly process, an Internet order process, or a hospital check-in process DPMO
becomes a convenient way to measure capability. When calculating DPMO, you dont
want to actually measure the defects over a million opportunities. That would take way
too long. Instead, the way you calculate DPMO is by using DPO as an estimate, like
this:
DPMO = DPO 1,000,000
This setup also means you can track backward, going from DPMO to DPO:

<img
src="http://d2r5da613aq50s.cloudfront.net/wp-content/uploads/357966.image6.jpg"
width="272" height="73" alt="image6.jpg"/>