Six Sigma for Process and

Quality Improvement

By:
Dr. Alisa Ibrahim
alisa.zamri@gmail.com
0192996424

1
Quality Management and Six
Sigma in Perspective
n Two primary sets of costs are involved
in quality:
¡ control costs
¡ failure costs
n Costs broken into four categories:
¡ Prevention costs
¡ Appraisal costs
¡ Internal costs of defects
¡ External costs of defects
2
Japanese Approaches to Quality

n In 1950 the Japanese government

invited W. Edwards Deming (then a
professor at New York University) to
give a series of lectures on quality
control to help Japanese engineers
reindustrialize the country.

3
W. Edwards Deming

n Major source of poor quality is

variation
n Quality improvement the responsibility
of top management
n All employees should be trained in use
of problem-solving tools and especially
statistical techniques

4
 Deming’s 14 Points
1. Create constancy of purpose
2. Adopt the new philosophy
3. Cease dependence on mass inspection
4. End practice of awarding business on
basis of price tags
5. Improve constantly and forever
6. Institute modern methods of training

5
Deming’s 14 Points continued

7. Institute modern method of

supervision
8. Drive out fear
9. Breakdown organizational barriers
10. Eliminate arbitrary numerical goals
11. Eliminate work standards and quotas
12. Remove barriers that reduce pride of
workmanship
6
Deming’s 14 Points continued

13. Institute a vigorous program of

education and training
14. Push the 13 points everyday

7
Total Quality Management (TQM)

n Better to produce item right the first

time than to try to inspect quality in
n Quality at the source - responsibility
shifted from quality control department
to workers

8
History of TQM
n Dr. Shewart began using statistical
control at the Bell Institute in 1930s
n Military standards developed in 1950s
n After World War II, Japanese Union of
Scientist and Engineers began
consulting with Deming
n Deming Prize introduced in Japan in
1951
9
History of TQM continued

n Quality assurance concept proposed in 1952

n Juran makes first trip to Japan in 1954
n Quality becomes Japan’s national slogan in
1956
n First quality circles created in 1957
n 10,000 quality circles by 1966
n 100,000 quality circles by 1977
n First U.S. quality circle 1974

10
Five Steps in TQM

n Determine what customers want

n Develop products and services
n Develop production system
n Monitor the system
n Include customers and suppliers

11
Joseph Juran
n Quality Control Handbook (1951)
n Employees speak in different languages
n Quality Trilogy
¡ Quality Planning
¡ Quality Control
¡ Quality Improvement
n Need to place more emphasis on
planning and improvement
12
 Joseph Juran continued

n Organizations progress through four

phases
¡ Minimize prevention and appraisal costs
¡ Appraisal costs increased
¡ Process control introduced increasing
appraisal costs but lowering internal and
external failure costs
¡ Prevention costs increased in effort to
lower total quality costs
13
A Brief History of Six Sigma
n The Six Sigma concept was developed by
Bill Smith, a senior engineer at Motorola, in
1986 as a way to standardize the way
defects were tallied.
n Sigma is the Greek symbol used in statistics
to refer to standard deviation which is a
measure of variation.
n Adding “six” to “sigma” combines a measure
of process performance (sigma) with the
goal of nearly perfect quality (six).

14
A Brief History of Six Sigma
n Since the 1920's the word “sigma”(s) has
been used by mathematicians and
engineers as a symbol for a unit of
Measurement in product quality variation.
n In the mid-1980's engineers in Motorola in
the USA used “Six Sigma”(S) an informal
name for an in-house initiative for reducing
defects in production processes, because it
represented a suitably high level of quality.

15
A Brief History of Six Sigma
n In the late-1980's Motorola extended the
Six Sigma methods to its critical business
processes, and significantly Six Sigma
became a formalized in-house 'branded'
name for a performance improvement
methodology, i.e, beyond purely 'defect
reduction.‘
n In 1991 Motorola certified its first 'Black Belt'
Six Sigma experts, which indicates the
beginnings of the formalization of the
accredited training of Six Sigma methods. 16
A Brief History of Six Sigma
n In 1995, Six Sigma became well known after
Mr. Jack Welch made it a central focus of
his business strategy at General Electric,
and today it is used in different sectors of
industry.
n By the year 2000, Six Sigma was effectively
established as an industry in its own right,
involving the training, consultancy and
implementation of Six Sigma methodology.

17
Definition
n In the popular book The Six Sigma Way,
Six Sigma is defined as:
¡ a comprehensive and flexible system for
achieving, sustaining and maximizing
business success. Six Sigma is uniquely
driven by close understanding of customer
needs, disciplined use of facts, data, and
statistical analysis, and diligent attention to
managing, improving, and reinventing
business processes. (p. xi)

18
Definition
n Six Sigma seeks to improve the quality of
process outputs by identifying and removing
the causes of defects.
n Six Sigma approach is a collection of
managerial and statistical concept and
techniques that focuses on reducing variation
in processes and preventing deficiencies in
product.
n The concept of Variation states “NO two
items will be perfectly identical.”

19
 Definition
n In a process that has achieved six sigma
capability, the variation is small compared to
the range of specification limit.
n A six sigma process is one in which
99.9999966% of the products manufactured
are statistically expected to be free of
defects (3.4 defects per million).
n Six Sigma is a very clever way of branding
and packaging many aspects of Total Quality
Management (TQM).
20
The Characteristics of Six
Sigma
n Statistical Quality Control
¡ Six Sigma is derived form the Greek letter σ (sigma
lowercase), which used to denote Standard Deviation in
statistics.
¡ Standard Deviation is used to measure variance which is
an important tool for measuring non-conformance as far
as the quality of the output is concerned

21
 The Characteristics of Six
Sigma
n Methodical Approach
¡ Six Sigma is a quality improvement strategy that features a well
defined methodical approach such as DMAIC.
n Fact and Data Based Approach
¡ The statistical and methodical aspects of Six Sigma show the
scientific basis of the technique. This accentuates an important
aspect of Six Sigma that it is fact and data based.
n Project and Objective Based Focus
¡ The Six Sigma process is implemented for an organization’s project
tailored to its specifications and requirement. The process is flexed to
suit the requirements and conditions in which a project is operating to
get the best results.
¡ Apart from that, the Six Sigma is also objective based.
¡ The management needs some incentive to invest in the Six Sigma
22
process. It is aimed to enhance profitability and to generate financial
 The Characteristics of Six
Sigma
n The Customer Focus
¡ The customer focus is fundamental to the Six Sigma approach.
The quality improvement and control standards are based on the
explicit customer requirements.
n Teamwork Approach to Quality Management
¡ The Six Sigma process requires organizations to get organized
when it comes to controlling and improving quality. Six Sigma
actually involves a lot of training depending on the role of an
individual in the Quality Management team.

23
 Six Sigma Objectives
n Overall Business Improvement
¡ Six Sigma methodology focuses on business improvement.
Beyond reducing the number of defects present in any given
number of products.
n Remedy Defects/Variability
¡ Any business seeking improved performance must reduce the
number of defective products or services it produces. Defective
products can harm customer satisfaction levels.
n Reduce Costs
¡ Reduced costs equal increased profits. A company
implementing Six Sigma principles has to look to reduce costs
wherever it possibly can without reducing quality.

24
 Six Sigma Objectives
n Improve Cycle Time
¡ Any reduction in the amount of time it takes to produce a product
or perform a service means money saved, both in maintenance
costs and personnel wages. Additionally, customer satisfaction
improves when both retailers and end users receive products
sooner than expected. The company that can get a product to
its customer faster may win the business.
n Increase Customer Satisfaction
¡ Customer satisfaction depends upon successful resolution of all
Six Sigma’s other objectives. But customer satisfaction is an
objective of its own.

25
Levels of Six Sigma

26
27
28
Methodologies

n Six Sigma projects follow two project

methodologies:
1. DMAIC
2. DMADV

These methodologies, composed of five phases. 29

Methodologies

n DMAIC
¡ used for projects aimed at improving an
exiting business process
n DMADV
¡ used for projects aimed at creating new
product or process designs

30
The DMAIC Improvement Process
n Six Sigma projects generally follow a
well defined process consisting of five
phases.
¡ define
¡ measure

¡ analyze

¡ improve

¡ control

pronounced dey-MAY-ihk
31
The DMAIC Improvement Process

32
33
The Define Phase
n The define phase of a DMAIC project focuses
on clearly specifying the problem or
opportunity, what the goals are for the
process improvement project, and what the
scope of the project is. Identifying who the
customer is and their requirements is also
critical given that the overarching goal for all
Six Sigma projects is improving the
organization’s ability to meet the needs of its
customers.
34
Defining and Measuring Quality
n Conformance to specifications
n Performance
n Quick response
n Quick-change expertise
n Features
n Reliability
n Durability
n Serviceability
n Aesthetics
n Perceived quality
n Humanity
n Value
35
 Benchmarking
n Benchmarking involves comparing an
organization's processes with the best
practices to be found. Benchmarking is
used for a variety of purposes, including:
¡ Comparing an organization's processes
with the best organization's processes.
¡ Comparing an organization's products and
services with those of other organizations.

36
Benchmarking continued

n Identifying the best practices to

implement.
n Projecting trends in order to be able to
respond proactively to future
challenges and opportunities.

37
Quality Function Deployment (QFD)

n Two key drivers of an organization’s long-

term competitive success are the extent to
which its new products or services meet
customers’ needs and having the
organizational capabilities to develop and
deliver such new products and services.
n Tools for helping translate customer desires
directly into product service attributes.

38
Four Houses of Quality

n Customer requirements
n Technical requirements
n Component requirements
n Process deployment requirements

39
House of Quality Details

40
The Measure Phase
n The measure phase begins with the
identification of the key process performance
metrics.
n Once the key process performance metrics
have been specified, related process and
customer data is collected.
n Two commonly used process performance
measures, namely, Defects per Million
Opportunities (DPMO) and Process Sigma.
41
Defects Per Million Opportunities

n Earlier it was noted that a literal

interpretation of Six Sigma is 3.4
defects per million opportunities
(DPMO). This may have caused some
confusion for more statistically inclined
readers, which we shall now attempt to
reconcile.

42
Defects Per Million Opportunities

43
Process Sigma

n How sigma itself can be used to

measure the performance of a
process.
¡ One way to measure the performance of
a process is to calculate the number of
standard deviations the customer
requirements are from the process mean
or target value.

44
DPMO for Alternative Process Sigma Levels

45
Motorola’s Assumption the Process Mean Can
Shift by as Much as 1.5 Standard Deviations

46
Comparison of 3 Sigma Process and 6 Sigma Process

47
 Comparison of 3 Sigma Process and 6 Sigma Process

q Three Sigma example

• Suppose a company that manufactures mobile devices is
progressing through Three Sigma after developing a new
component. The company currently has an output capacity of
275,000 units. Assuming a 93.3% accuracy rate, the company is
allowing for up to 18,425 defects with 256,575 products that meet
quality control standards. As this value represents a high margin of
error relative to the standard deviation, the company may establish
short-term objectives that maximize efficiency and support
involvement for all departments. With these considerations, the
company focuses on goals to improve quality and performance to
advance at each Sigma level.

48
 Comparison of 3 Sigma Process and 6 Sigma Process

q Six Sigma example

• Assume the previous example company achieves a Six Sigma
level of quality and accuracy when manufacturing the new mobile
device components. In addition to these improvements, the
company can also produce 780,000 components due to its growth.
Assuming an accuracy rate of 99.999997%, the company can
expect only 0.0234 parts of a component to experience defects
with 779,999.9766 products meeting quality control standards.
This represents a near-perfect accuracy rate, which is essential to
aim for when implementing the Six Sigma methodology.

49
The Analyze Phase

n In this phase our objective is to utilize

the data that has been collected to
develop and test theories related to the
root causes of existing gaps between
the process’ current performance and
its desired performance.
n See next slide Table 4.3 Common
tools and methodologies in the Six
Sigma toolset.
50
Brainstorming
n The brainstorming approach:
¡ Do not criticize ideas during the
brainstorming session.
¡ Express all ideas no matter how radical,
bizarre, unconventional, ridiculous, or
impractical they may seem.
¡ Generate as many ideas as possible.
¡ Combine, extend, and/or improve on one
another’s ideas.
51
Brainstorming: Actions to Enhance
Team Creativity
n Create diversified teams.
n Use analogical reasoning.
n Use brain writing.
n Use the Nominal Group Technique.
n Record team ideas.
n Use trained facilitators to run the brainstorming
session.
n Set high standards.
n Change the composition of the team.
n Use electronic brainstorming.
n Make the workplace a playground.
52
Cause and Effect Diagrams

53
Process Capability Analysis

54
Process Capability Analysis
continued

55
The Improve Phase: Design of
Experiments (DOE)

n OFAT and 1FAT - one factor at a time.

¡ Shortcomings
n Not typically possible to test one factor at a
time and hold all the other factors constant.
n Not possible to account for interactions or
joint variation between variables (Figure
4.16).

56
DOE continued
Obtaining good results from a DOE involves these
seven steps:
n Set objectives.

n Select process variables.

n Select an experimental design.

n Execute the design.

n Check that the data are consistent with the

experimental assumptions.
n Analyze and interpret the results.

n Use/present the results (may lead to further runs or

DOE's).
57
DOE continued

n Some of the major considerations

associated with DOE include:
¡ Determining which factors to include in
the experiment.
¡ Specifying the levels for each factor.
¡ Determining how much data to collect.
¡ Determining the type of experimental
design.
58
Taguchi Methods

n Design for Manufacturability (DFM)

n Procedure for statistical testing to
determine best combination of product
and transformation system design that
will make output relatively independent
of normal fluctuations in the production
system

59
Statistical Quality Control

60
Chance Versus Assignable Variation

n Chance variation is variability built into

the system.
n Assignable variation occurs because
some element of the system or some
operating condition is out of control.
n Quality control seeks to identify when
assignable variation is present so that
corrective action can be taken.
61
 Chance Versus Assignable Variation

Chance Causes Assignable Causes

(i) Consist of many individual causes. Consists of one or just a few individual causes.

(ii) Any one chance causes results in only a minute amount of

variation. (However, many of the chance causes act Any one assignable cause can result in a large amount of
simultaneously so that the total amount of chance variation is variation.
substantial).

(lit) Some typical chance causes of variation are :

(a) Slight variations in raw material (though within Some typical assignable causes of variation are : Batch of
the specifications) (6) Slight vibration of machine (c) Lack of defective raw material
human perfection in reading instruments Faulty set up Untrained operator
and setting controls.

(jy) As a practical matter, chance variation cannot The presence of assignable variation can be detected and
economically be eliminated from a process. action to eliminate the causes is usually justified.

62
Control Based on Attributes and
Variables

n Inspection for Variables: measuring a

variable that can be scaled such as
weight, length, temperature, and
diameter.
n Inspection of Attributes: determining
the existence of a characteristic such as
acceptable-defective, timely-late, and
right-wrong.
63
Control Charts

64
 Control Charts

n Developed in 1920s to distinguish

between chance variation in a system
and variation caused by the system’s
being out of control - assignable
variation.

65
Control Charts continued
n Repetitive operation will not produce
exactly the same outputs.
n Pattern of variability often described by
normal distribution.
n Random samples that fully represent the
population being checked are taken.
n Sample data plotted on control charts to
determine if the process is still under
control.
66
Control Chart with Limits Set at Three Standard
Deviations

67
Control Charts for Variables

68
Two Control Charts
n Sample Means Chart
n Range Chart

69
Control Limits
Sample Means Chart:

UCL X = X + A 2 R
LCL X = X - A 2 R

Range Chart:

UCL R = D 4 R
LCL R = D 3 R

70
Calculating the Grand Mean and the
Average Range

X=
å X
N

R=
å R
N

71
Mean Age of Ice Cream

72
Range in Ice Cream Age

73
Control Charts for Attributes

74
Fraction-Defective (p) Charts
total number of defects
p=
total number of units sampled
p (1 - p )
sp =
n

UCL p = p + zs p
LCL p = p - zs p
75
Number-of-Defects (c) Charts

number of incidents observed

c=
number of units sampled
sc = c

UCL c = c + zs c
LCL c = c - zs c

76
Six Sigma in Practice
n Six Sigma Roles:
¡ Master Black Belts.
¡ Black Belts.
¡ Green Belts.
¡ Yellow Belts.
n Supporting Roles:
¡ Champions/Sponsors.
¡ Process owners.
77
78
Six Sigma Software
n Arena
n ARIS Six Sigma
n Bonita Open Solution BPMN2 standard and KPIs for statistic
monitoring
n JMP
n Mathematical
n MATLAB or GNU Octave
n Microsoft Visio
n STATA
n STATISTICA
And Many more…..

79
Criticism of Six Sigma
n The use of "Black Belts" as itinerant change agents
has (controversially) fostered an industry of training
and certification.
n Critics argue there is overselling of Six Sigma by
too great a number of consulting firms, many of
which claim expertise in Six Sigma when they have
only a rudimentary understanding of the tools and
techniques involved, or the markets or industries in
which they are acting.

80
Quality in Services
n Measuring is difficult
n Training in standard procedures often
used to improve quality
n One way to measure quality of services
is to use customer satisfaction surveys
n J.D. Power and Associates uses
surveys to rate domestic airlines, hotel
chains, and rental car companies.

81
Rating the Performance of Domestic
Airlines

n On-time performance (25%)

n Airport check-in (11%)
n Courtesy of flight attendants (11%)
n Seating comfort (11%)

Chapter 4: Six Sigma for Process and Quality 82

Improvement
Service Defections

n Organizations should monitor

customer defections
¡ feedback from defecting customers can
be used to identify problem areas
¡ can determine what is needed to win
them back
¡ changes in defection rate can be used as
early warning signal
83
Quality Awards/Certifications

84
The Malcolm Baldrige National Quality
Award

85
ISO 9000

n Guidelines for designing,

manufacturing, selling, and servicing
products.
n Selecting an ISO 9000 certified
supplier provides some assurance that
supplier follows accepted business
practices in areas covered by the
standard
86
 Elements of ISO 9000
n Management Responsibility n Control of Inspection,
n Quality System Measuring, and Test
n Contract Review Equipment
n Design Control n Inspection and Test Status
n Document and Data Control n Control of Nonconforming
n Purchasing Product
n Control of Customer Supplied
Product n Corrective and Preventive
n Product Identification and Traceability Action
n Process Control n Handling, Storage,
n Inspection and Testing Packaging, Preservation, and
Delivery
n Internal Quality Audits
n Training
n Servicing
n Statistical Techniques

87
88
ISO 14000
n Series of standards covering environmental
management systems, environmental
auditing, evaluation of environmental
performance, environmental labeling, and
life-cycle assessment.
n Intent is to help organizations improve their
environmental performance through
documentation control, operational control,
control of records, training, statistical
techniques, and corrective and preventive
actions.
89
90
91