OPERATIONS MANAGEMENT

with Gopesh Anand

MODULE 4
Quality Management
Lesson 4-1
Principles and Programs
Video 4-1.1
Lesson Objectives
LESSON 4-1 OBJECTIVES

By the end of this lesson you will be

able to:
Recognize the multiple aspects of quality.
Understand the principles underlying total
quality management.
See the role of quality management
initiatives in organizations.
Distinguish between different costs of
quality.
OPERATIONS MANAGEMENT

with Gopesh Anand

MODULE 4
Quality Management
Lesson 4-1
Principles and Programs
Video 4-1.2
Defining Quality
IN-VIDEO QUESTION 1

What words can you think of

to define “good quality” for
products – goods and
services – that you use day-
to-day?
IN-VIDEO QUESTION 1

What words can you think of

to define “good quality” for
products – goods and
services – that you use day-
to-day?

(flickr.com/taymazvalley, 2010)
IN-VIDEO INSIGHTS 1

What words can you think of

to define “good quality” for
products – goods and
services – that you use day-
to-day?
GOOD QUALITY FROM
CUSTOMER PERSPECTIVE

Excellence
Features
Perfection
Consistency
Exceed expectations
Value
Durability
CUSTOMER NEEDS FROM
PRODUCER PERSPECTIVE

Providing a good, usable product

Total customer service and
satisfaction
Eliminating waste
Availability
Compliance with policies and
procedures
Doing it right the first time
Delighting customers
RELEVANCE OF BETTER QUALITY FOR BUSINESS

Improved quality Improved quality

of design of conformance
Higher Higher Lower production
perceived value prices costs

Higher sales Increased

revenues
Higher profitability
DIMENSIONS OF QUALITY – PRODUCT

A product’s primary operating characteristics

Performance Gas mileage of a car
Promptness of restaurant service

Supplements to basic performance

Features Built in Wi-Fi (without much price premium)
Personalization of service

Meet specified tolerances

Conformance Size of window replacement
Bandwidth of Internet service
(Garvin, 1987)
DIMENSIONS OF QUALITY – LONG TERM

Probability of product breaking down in a period of time

Reliability
Time until first repair for a car
Service interruptions for Internet service

Extent of use before deterioration or obsolescence

Durability When replacement of car trumps repairs
Time before software becomes outdated
Ease of repairs and experience of service
Serviceability Turnaround time for car repairs
Knowledge level of cable repair person
(Garvin, 1987)
DIMENSIONS OF QUALITY – SUBJECTIVE
ASPECTS

Individual preferences related to five human senses

Aesthetics Dashboard of car
Smell in a coffee shop
Car service wait room with visible service area

Perceived Indirect cues to product quality

Quality Reputation and user-reviews
Interaction with nurse and physician
Manner in which wait time is divided in a doctor visit
GAP MODEL FOR SERVICE QUALITY

(Parasuraman et al., 1985)

GAP MODEL FOR SERVICE QUALITY

(Parasuraman et al., 1985)

GAP MODEL FOR SERVICE QUALITY

(Parasuraman et al., 1985)

GAP MODEL FOR SERVICE QUALITY

(Parasuraman et al., 1985)

GAP MODEL FOR SERVICE QUALITY

(Parasuraman et al., 1985)

GAP MODEL FOR SERVICE QUALITY

(Parasuraman etetal.,
(Parasuraman al.,1985)
1985)
DEFINING QUALITY

“The difficulty in defining quality is to

translate future needs of the user
into measurable characteristics so
that a product can be designed and
turned out to give satisfaction at a
price that the user will pay.”
(Deming, 1986; p. 169)
COMPREHENSIVE
APPROACH TO QUALITY

Fitness for purpose or use

Goods and services with features for
customers and free from defects
Include internal process customers
Include entire lifespan of product
Design, supplier relations, production
processes, quality control, quality checks,
distribution, and after-sales
(Juran, 1988)
REFERENCE
Academic Citations
Garvin, D. A. (1987). Competing on the 8 dimensions of quality. Harvard Business Review, 65(6), 101-109. Retrieved
from https://hbr.org/1987/11/competing-on-the-eight-dimensions-of-quality
Juran, J. M. (1988). Quality control handbook (4th ed.). New York, NY: McGraw-Hill.
MIT Center for Advanced Engineering. (1986). Out of crisis. Cambridge, MA: Deming, W. Edwards
Parasuraman, A., Zeithaml, V. A., & Berry, L. L. (1985). A conceptual model of service quality and its implications for
future research. Journal of Marketing, 49(4). 41-50. doi: 10.2307/1251430

Image Credits
Valley, T. (2010). Think [Online image]. Retrieved October 7, 2015 from
https://www.flickr.com/photos/taymazvalley/5209251530/
OPERATIONS MANAGEMENT

with Gopesh Anand

MODULE 4
Quality Management
Lesson 4-1
Principles and Programs
Video 4-1.3
Origin and Evolution
1980S QUALITY
REVOLUTION IN U.S.
Walter A. Shewhart – Continuous
improvement cycles
W. Edwards Deming – Management
responsibility
Joseph M. Juran – Planning for quality
Genichi Taguchi – Experimental design
Kaoru Ishikawa – Quality circles
Armand V. Feigenbaum – Total quality
control
Philip B. Crosby – Zero defects
QUALITY MANAGEMENT
SYSTEMS

Quality Management Systems

consist of systematic efforts to
seek out and apply new ways of
doing work, i.e., actively and
repeatedly making process
improvements.
(Anand et al., 2009)
IN-VIDEO QUESTION 2

As customers, we frequently rely on

certifications aimed at providing
confidence about the quality of the
products we purchase.

Try to recall one such certification

that you have seen on product
packaging or a company website.

(flickr.com/taymazvalley, 2010)
IN-VIDEO INSIGHTS 2

As customers, we frequently rely on

certifications aimed at providing
confidence about the quality of the
products we purchase.

Try to recall one such certification

that you have seen on product
packaging or a company website.
CERTIFICATION
STANDARDS

Verification of effective quality

assurance systems
International Organization for
Standardization
ISO 9000 series
ISO 14000 series

U.S. Food and Drug Administration

Good Manufacturing Practices

Bureau of Indian Standards

Certification for products
QUALITY AWARDS

Recognition of excellence in quality

management

Award criteria useful for self-

evaluation
Deming Award
Malcolm Baldrige National Quality Award
EFQM Award
Shingo Prize
EVOLUTION OF QUALITY
PRACTICES AND SYSTEMS

1970s 1980s 1990s

Quality
Circles TQM ISO 9000 Agile
Business
Process Learning
SPC Just in Time Reengineering organization
Self-
managed Baldrige
teams Framework Lean Six Sigma
Theory of Capability
Constraints Maturity Model
(Cole, 1998; Garvin, 1988)
REASONS FOR CONSTANT
RENEWAL

Resistance to change
Need cross-functional work
Operational improvements not
publicized
Operational metrics not used, even if
assessed
Control vs. improvement vs.
innovation
LINKS TO OTHER
FUNCTIONS (1 OF 2)

Marketing – Customer expectations

and feedback

Finance – Assess value of changes

Accounting – Metrics for operations

Human Resource Management –

Hiring, training, compensation, and
development of employees
LINKS TO OTHER
FUNCTIONS (2 OF 2)

Research and Development –

Product design

Engineering – Process design

Information Systems – Capture data

and provide real-time process
feedback

Analytics – Detect patterns in

demand and production data
SIX SIGMA

A business improvement approach

That seeks to find and eliminate causes
of defects
In manufacturing, service, and
transactional processes
To result in clear financial returns for the
organization

Main focus: Reduce process

variation
(www.isixsigma.com)
Top: (motorola.com, n.d.) Bottom (ge.com, n.d.)
LEAN MANAGEMENT

A business improvement approach

that aims for a continuous
improvement culture to create
smooth flow for goods and services
through value streams.

Main focus: Reduce waste

(www.lean.org)
Top: (toyota.com, n.d.) Bottom (lean.org, n.d.)
WIDELY ADOPTED INITIATIVES

(All trademarks are owned by their respective companies)

PRINCIPLES, PRACTICES,
AND PROGRAMS

Quality philosophers focused on

principles
Applied the principles using certain
practices

Companies have adopted practices

Combined the practices into programs
REFERENCE
Academic Citations
Anand, G., Ward, P. T., Tatikonda, M. V., & Schilling, D. A. (2009). Dynamic capabilities through continuous
improvement infrastructure. Journal of Operations Management, 27(6), 444-461. doi:10.1016/j.jom.2009.02.002
Cole, R. E. (1998). Learning from the quality movement: What did and didn't happen and why?. California management
review, 41(1), 43. doi: 10.2307/41165975
Garvin, D. (1988) Managing Quality: The Strategies and Competitive Edge. New York, NY: The Free Press
REFERENCE
Image Credits
ADM [Online image]. Retrieved October 7, 2015 from http://www.adm.com/en-US/Pages/default.aspx
Bank of America [Online image]. Retrieved October 7, 2015 from https://www.bankofamerica.com/
Cardinal Health [Online image]. Retrieved October 7, 2015 from http://www.cardinalhealth.com/en.html
Caterpillar [Online image]. Retrieved October 7, 2015 from http://www.caterpillar.com/
Chevron [Online image]. Retrieved October 7, 2015 from http://www.chevron.com/
Ford [Online image]. Retrieved October 7, 2015 from http://www.autobytel.com/ford/fiesta/2011/car-buying-
guides/2012-ford-fiesta-gets-new-options-for-better-customization-105941/
Freddie Mac [Online image]. Retrieved October 7, 2015 from http://www.freddiemac.com/
General Electric [Online image]. Retrieved October 7, 2015 from http://www.ge.com/
Home Depot [Online image]. Retrieved October 7, 2015 from http://www.homedepot.com/
HP [Online image]. Retrieved October 7, 2015 from http://www8.hp.com/us/en/home.html
REFERENCE
Image Credits
iSixSigma [Online image]. Retrieved October 7, 2015 from http://www.isixsigma.com/
Lean Enterprise Institute [Online image]. Retrieved October 7, 2015 from http://www.lean.org/
Merrill Lynch [Online image]. Retrieved October 7, 2015 from https://www.ml.com/
Motorola [Online image]. Retrieved October 7, 2015 from http://www.motorola.com/us/home
Toyota [Online image]. Retrieved October 7, 2015 from http://www.toyota.com/
UPS [Online image]. Retrieved October 7, 2015 from http://www.ups.com/
Valley, T. (2010). Think [Online image]. Retrieved October 7, 2015 from
https://www.flickr.com/photos/taymazvalley/5209251530/
Walmart [Online image]. Retrieved October 7, 2015 from http://www.walmart.com/
Wells Fargo [Online image]. Retrieved October 7, 2015 from https://www.wellsfargo.com/
OPERATIONS MANAGEMENT

with Gopesh Anand

MODULE 4
Quality Management
Lesson 4-1
Principles and Programs
Video 4-1.4
Common Elements
STRUCTURE OF QUALITY MANAGEMENT
PROGRAMS

(Anand, Ward, Tatikonda, & Schilling,

ORGANIZATIONAL
ELEMENTS

Committed leadership

Cross-functional process view

Total systems perspective

Supplier involvement

Measurement

Reduction in process variation

(Sitkin et al.,1994; Anderson et al., 1994; Hackman, & Wageman, 1995)
EMPLOYEE INVOLVEMENT
ELEMENTS
Goal setting
Continuous improvement and learning
Employee training in improvement
methods
Employee participation in improvement
Frontline employee empowerment –
quality at source
Teamwork
(Sitkin et al.,1994; Anderson et al., 1994; Hackman, & Wageman, 1995)
COST OF QUALITY

Cost of Good Quality Cost of Poor Quality

Prevention Appraisal Internal External

Costs Costs Failure Costs Failure Costs

(Crosby, 1979, 1996; Feigenbaum, 1956; Juran 1999)

EXPENSES FOR PRODUCING
GOOD QUALITY (1 0F 2)

Prevention Costs
Prevent defects and errors in processes
and products
Also aimed at limiting appraisal and
failure costs
Examples: Quality planning, product design,
process design, supplier selection, employee
training
EXPENSES FOR PRODUCING
GOOD QUALITY (2 0F 2)

Appraisal Costs
Control quality at all stages of products
and processes
Examples: Inspection of purchased materials
and services, in-process checks, final
inspections, field tests
EXPENSES AS A RESULT
OF BAD QUALITY (1 OF 2)

Internal Failure
Non-conforming goods and services
Found before delivery to external
customers
Examples: Scrap, rework, retesting,
downgrading, delays, employee frustration
and discouragement
EXPENSES AS A RESULT
OF BAD QUALITY (2 OF 2)

External Failure
Defects found after delivery to customers
Examples: Complaint handling, goods
repairs, service recoveries, warranties –
returns and replacements, customer
dissatisfaction
TRADITIONAL VIEW OF TOTAL COST OF QUALITY

Total Cost of Quality

Cost

Costs of Costs of
Failures Prevention
and
Appraisal
Optimum

100% 100%
Level of Quality
Defective Good
(Juran, 1999)
CHANGES TO THE MODEL

Costs of nonconformance
underestimated

Synergies of proactive efforts

unrecognized

Low cost and better quality not

contrary goals
(Cole, 1992)
JUSTIFICATION FOR CONTINUOUS
IMPROVEMENT
Total Quality Cost

Costs of
Failures
Cost

Costs of
Prevention
and
Appraisal
100% 100%
Level of Quality
Defective Good
(Schneiderman, 1986; Juran, 1979, p. 5-12)
POTENTIAL PAYOFF FROM CONTINUOUS
IMPROVEMENT (CI)

(Crosby, 1979, 1996; Juran 1999)

ILLUSTRATION OF COSTS
OF QUALITY
Based on information about the
expenses in the four categories of costs
of quality in Company X
Note the typical costs in each category.
Calculate their impact related to each
other.
Calculate their impact related to annual
sales.
Observe how a quality improvement
initiative could change these expenses.
PREVENTION COSTS

Extra work hours spent on:

Product design $ 10,000
Quality improvement projects $ 5,000
Preventive maintenance $ 2,000
CI program training $ 2,000

Additional material expenses:

High quality raw material $ 400
Robust product engineering $ 600
$ 20,000
APPRAISAL COSTS

Expenses:
Incoming inspection work hours $ 20,000
In-process inspection work hours $ 10,000
Outgoing inspection work hours $ 34,000
Inspector training $ 30,000
Inspector certification fees $ 1,000
External certifications $ 3,000
Rent for inspection space $ 10,000
Cost of destructive inspection $ 2,000
$ 110,000
INTERNAL FAILURE COSTS

Work hours spent on:

Rework $ 70,000
Compensatory production $ 50,000

Materials for:
Rework $ 55,000
Compensatory production $ 41,000
Rent for rework space $ 24,000
$ 240,000
EXTERNAL FAILURE
COSTS
Expenses
Products returned $ 100,000
Work hours spent on processing returns $ 10,000
Work hours spent on products returned $ 10,000
Work hours spent on customer interactions $ 25,000
Travel $ 30,000
Compensation to customer $ 100,000
Legal fees $ 55,000
$ 330,000
LET’S DO THE NUMBERS:
COMPUTE IMPACTS OF COSTS
Sales $3,000,000
Costs of Quality (COQ) Current % of COQ
Prevention $ 20,000
Appraisal $ 110,000
Internal Failure $ 240,000
External Failure $ 330,000
$ 700,000
Total Cost of Quality
as share of sales
Cost of Poor Quality
as share of sales
(Dugdale, 2010)
IN-VIDEO QUESTION 3:
COMPUTE IMPACTS OF COSTS
Sales $3,000,000
Costs of Quality (COQ) Current % of COQ
Prevention $ 20,000
Appraisal $ 110,000
Internal Failure $ 240,000
External Failure $ 330,000
$ 700,000
Total Cost of Quality
as share of sales
Cost of Poor Quality
as share of sales
(flickr.com/taymazvalley, 2010)
IN-VIDEO INSIGHTS 3:
COMPUTE IMPACTS OF COSTS
Sales $3,000,000
Costs of Quality (COQ) Current % of COQ
Prevention $ 20,000 3%
Appraisal $ 110,000 16%
Internal Failure $ 240,000 34%
External Failure $ 330,000 47%
$ 700,000
Total Cost of Quality 23%
as share of sales
Cost of Poor Quality 19%
as share of sales
LET’S DO THE NUMBERS:
COSTS OF QUALITY WITH CONTINUOUS IMPROVEMENT
Sales $3,000,000
With Continuous Improvement
Costs of Quality (COQ) Current % of COQ Potential % of COQ
Prevention $ 20,000 3% $ 200,000
Appraisal $ 110,000 16% $ 55,000
Internal Failure $ 240,000 34% $ 15,000
External Failure $ 330,000 47% $ 10,000
$ 700,000 $ 280,000
Total Cost of Quality 23%
as share of sales
Cost of Poor Quality 19%
as share of sales
(Dugdale, 2010)
IN-VIDEO QUESTION 4:
COSTS OF QUALITY WITH CONTINUOUS IMPROVEMENT
Sales $3,000,000
With Continuous Improvement
Costs of Quality (COQ) Current % of COQ Potential % of COQ
Prevention $ 20,000 3% $ 200,000
Appraisal $ 110,000 16% $ 55,000
Internal Failure $ 240,000 34% $ 15,000
External Failure $ 330,000 47% $ 10,000
$ 700,000 $ 280,000
Total Cost of Quality 23%
as share of sales
Cost of Poor Quality 19%
as share of sales
(flickr.com/taymazvalley, 2010)
IN-VIDEO INSIGHTS 4:
COSTS OF QUALITY WITH CONTINUOUS IMPROVEMENT
Sales $3,000,000
With Continuous Improvement
Costs of Quality (COQ) Current % of COQ Potential % of COQ
Prevention $ 20,000 3% $ 200,000 71%
Appraisal $ 110,000 16% $ 55,000 20%
Internal Failure $ 240,000 34% $ 15,000 5%
External Failure $ 330,000 47% $ 10,000 4%
$ 700,000 $ 280,000
Total Cost of Quality 23% 9%
as share of sales
Cost of Poor Quality 19% 1%
as share of sales
JURAN’S CONTINUOUS
IMPROVEMENT TRILOGY

Quality Planning
Identify customers and determine their
needs
Develop products to fulfill customer needs

Quality Control
Produce the product under operating
conditions with minimal inspection

Quality Improvement
Optimize the processes
(Juran, 1986)
JURAN TRILOGY

(Juran, 1986)
MANAGING PROCESS
VARIATION

"The central problem of

management ... is to understand
better the meaning of variation, and
to extract the information contained
in variation.”
(Deming, 1986, p. 20)

“If I had to reduce my message for

management to just a few words, I’d
say it all had to do with reducing
variation.”
(Neave, 1990, p. 57)
REFERENCE
Academic Citations
Anand, G., Ward, P. T., Tatikonda, M. V., & Schilling, D. A. (2009). Dynamic capabilities through continuous
improvement infrastructure. Journal of Operations Management, 27(6), 444-461. doi:10.1016/j.jom.2009.02.002
Anderson, J. C., Rungtusanatham, M., & Schroeder, R. G. (1994). A theory of quality management underlying the
Deming management method. Academy of Management Review, 19(3), 472-509. doi: 10.5465/AMR.1994.9412271808
Cole, R. E. (1992). The quality revolution. Production and Operations Management, 1(1), 118-120. doi: 10.1111/j.1937-
5956.1992.tb00343.x
Crosby, P. (1979). Quality is free: The art of making quality certain. New York, NY: McGraw Hill
Crosby, P. (1996). Quality is still free: Making quality certain in uncertain times. New York, NY: McGraw-Hill
Feigenbaum, A. V. (1956). Total quality-control. Harvard Business Review, 34(6), 93-101. Retrieved from https://hbr.org/
Hackman, J. R., & Wageman, R. (1995). Total quality management: Empirical, conceptual, and practical issues.
Administrative Science Quarterly, 40(2), 309-342. doi: 10.2307/2393640
REFERENCE
Academic Citations
Juran, J. M. (1986). The quality trilogy. Quality Progress, 19(8), 19-24. Retrieved from
http://asq.org/qualityprogress/index.html
Juran, J.M. (1979). Quality control handbook (3rd ed.). New York, NY: McGraw Hill
Juran, J.M. (1999). Quality control handbook (5th ed.). New York, NY: McGraw Hill
MIT Center for Advanced Engineering. (1986). Out of crisis. Cambridge, MA: Deming, W. Edwards
Neave, H. (1990). The Deming dimension. Knoxville, TN: SPC Press, Inc.
Schneiderman, A. M. (1986). Optimum quality costs and zero defects: are they contradictory concepts? Quality
Progress, 19(11), 28-31. Retrieved from
http://www.schneiderman.com/AMS_publications/Optimum%20Quality%20Costs/optimum.pdf
Sitkin, S. B., Sutcliffe, K. M., & Schroeder, R. G. (1994). Distinguishing control from learning in total quality
management: A contingency perspective. Academy of Management Review, 19(3), 537-564. doi:
10.5465/AMR.1994.9412271813
REFERENCE
Image Credits
Dugdale, D. (2010). Analyzing financial data [Online image]. Retrieved October 7, 2015 from
https://www.flickr.com/photos/davedugdale/5099605109/
Valley, T. (2010). Think [Online image]. Retrieved October 7, 2015 from
https://www.flickr.com/photos/taymazvalley/5209251530/
OPERATIONS MANAGEMENT

with Gopesh Anand

MODULE 4
Quality Management
Lesson 4-1
Principles and Programs
Video 4-1.5
Lesson Recap
LESSON 4-1 RECAP

In this lesson you learned how to:

Define quality based on different
perspectives.
Appreciate the views of quality
management philosophers.
Recognize the evolution of quality
management initiatives.
Compute costs of quality.
OPERATIONS MANAGEMENT

with Gopesh Anand

MODULE 4
Quality Management
Lesson 4-2
Variability Assessment
Video 4-2.1
Lesson Objectives
LESSON 4-2 OBJECTIVES

By the end of this lesson you will be

able to:
Recognize the implications of variability
in processes.
Understand the principles underlying
statistical process control (SPC).
Use SPC analysis for different data
types.
Assess process performance.
OPERATIONS MANAGEMENT

with Gopesh Anand

MODULE 4
Quality Management
Lesson 4-2
Variability Assessment
Video 4-2.2
Statistical Process Control
SOURCES OF VARIABILITY
IN-VIDEO QUESTION 5

Consider your daily commute. What

factors impact your estimate of the
time it takes? Think in terms of the
sources:
Materials
Tools
Operators
Methods
Machines
Environment
Measurement instruments
Measurement accuracy
IN-VIDEO QUESTION 5

Consider your daily commute. What

factors impact your estimate of the
time it takes? Think in terms of the
sources:
Materials
Tools
Operators
Methods
Machines
Environment
Measurement instruments
Measurement accuracy
(flickr.com/taymazvalley, 2010)
IN-VIDEO INSIGHTS 5

Consider your daily commute. What

factors impact your estimate of the
time it takes? Think in terms of the
sources:
Materials
Tools
Operators
Methods
Machines
Environment
Measurement instruments
Measurement accuracy
CATEGORIZING CAUSES
OF VARIABILITY

Common cause:
Expected variation – Controlled variation
Exists within the process
Is a measure of the process's potential,
or how well the process can perform
Special cause:
Unexpected variation – Uncontrolled
variation
Comes from outside the process
Variation that is beyond common cause
variation (Deming, 1986)
STATISTICAL PROCESS
CONTROL (SPC)

Methodology for:
Establishing inherent potential of process
based on expected routine performance
Monitoring process to identify occurrence
of special causes of variation

Consists of development and use of

process control charts
DEVELOPING CONTROL
CHARTS (1 OF 2)

Prepare
Choose measurement and determine
data collection plan
Collect data
Calculate statistics – mean and standard
deviation
DEVELOPING CONTROL
CHARTS (2 OF 2)

Determine trial control limits

Center line (CL), upper control limit
(UCL), and lower control limit (LCL)
Analyze and interpret results
Determine if in control
Eliminate out-of-control points
Recalculate control limits as necessary
USING CONTROL CHARTS
Collect and plot data
… at predetermined intervals
… and using predetermined sample size
For point beyond control limit
Correct the immediate problem
Conduct root cause analysis
Or
Recognize exceptional performance
Figure out ways to replicate
Observe patterns
Recalculate control limits as necessary
GENERAL STRUCTURE OF CONTROL CHARTS

Control
Upper
Average
Limit + 3 * standard deviation Regularly scheduled samples
Measurement

in chronological order
Center

Process
Line

Average
Control
Lower

Average
Limit

- 3 * standard deviation
SOME CAUTION PATTERNS

Sudden shift in point clusters

Cycles

Trends

Concentrated at the center line

UNDERLYING BASIS:
NORMAL DISTRIBUTION

µ = Population Mean σ = Standard Deviation

(Kernler, 2014)
DIFFERENT CONTROL CHARTS
REFERENCE
Academic Citations
MIT Center for Advanced Engineering. (1986). Out of crisis. Cambridge, MA: Deming, W. Edwards

Image Credits
Kernler, D. (2014). Empirical rule [Online image]. Retrieved October 7, 2015 from
https://commons.wikimedia.org/wiki/File:Empirical_Rule.PNG
Valley, T. (2010). Think [Online image]. Retrieved October 7, 2015 from
https://www.flickr.com/photos/taymazvalley/5209251530/
OPERATIONS MANAGEMENT

with Gopesh Anand

MODULE 4
Quality Management
Lesson 4-2
Variability Assessment
Video 4-2.3
Attribute Data Control Charts
Proportion Data
EXAMPLE: DEFECTIVE
SUBASSEMBLIES
A car parts supplier takes and tests weekly
samples of 15 subassemblies for truck doors
put together on an assembly line.

Over 10 weeks, the inspector records the

number of defective subassemblies
regardless of the extent to which any one is
defective.

Please help the inspector construct a control

chart for the performance of the assembly
line.
SAMPLES OF SIZE 15
OVER TEN WEEKS
Defective
Week Number
Subassemblies
1 3
2 1
3 0
4 0
5 0
6 2
7 0
8 5
9 1
10 0
LET’S DO THE NUMBERS

(Dugdale, 2010)
P CHART

Center line
Mean of sample proportions
p-bar or p

Upper and lower control limits

Mean + and − 3 standard deviations

p (1 − p )
p±3
n
P CHART CENTER LINE
AND CONTROL LIMITS

Computing proportions:
Sample 1: 3 ÷ 15 = 0.20
Sample 2: 1 ÷ 15 = 0.067

Center line for control chart:

Mean of 10 sample proportions
OR
Total defective subassemblies
÷ Total inspected subassemblies
CONTROL LIMITS

Defective Mean proportion = 0.08

Week Number Proportion
Standard deviation =
1 3 0.200
2 1 0.067
Sq. root {(0.08*0.92) ÷ 15}
3 0 0.000
4 0 0.000 = 0.070
5 0 0.000
6 2 0.133 UCL = 0.08 + 3 * 0.070
7 0 0.000
= 0.29
8 5 0.333
9 1 0.067
LCL = 0.08 − 3 * 0.070
10 0 0.000 = - 0.13 →0
P CHART

P Chart of Defective Subassemblies

0.35 1

0.30
UCL=0.2901

0.25
Proportion

0.20

0.15

0.10 _
P=0.08
0.05

0.00 LCL=0

1 2 3 4 5 6 7 8 9 10
Sample

Output from Minitab® Software

INTERPRETATION
Week 8 proportion defective is
higher than upper control limit
Look into reason
Reasonably clear?
Special cause?
Will not ordinarily occur?

If yes, delete sample and recalculate

control limits
If no, collect fresh data under
controlled conditions
MODIFIED CONTROL LIMITS

Defective Mean proportion = 0.052

Week Number Proportion
Standard deviation =
1 3 0.200
2 1 0.067
Sq. root {(0.052*0.948) ÷ 15}
3 0 0.000
4 0 0.000 = 0.057
5 0 0.000
6 2 0.133 UCL = 0.052 + 3 * 0.057
7 0 0.000
= 0.224
9 1 0.067
10 0 0.000
LCL = 0.052 - 3 * 0.057
= - 0.120 →0
MODIFIED P CHART
Note: Samples 8 and 9 are for weeks 9 and 10.

P Chart of Defective Subassemblies

0.25

UCL=0.2236
0.20

0.15
Proportion

0.10

_
0.05 P=0.0519

0.00 LCL=0

1 2 3 4 5 6 7 8 9
Sample

Output from Minitab® Software

INTERPRETATION

The current process is expected to

have a 0 to 22% defect rate.
Less than 22% defective can be
attributed to common causes
Greater than 22% proportion defective is
an indication of possible special causes

Based on context
Consider number of samples to calibrate
control chart
USE OF P CHART
Study classification type attribute data,
e.g., proportion of non-conforming items
by month
Subgroup sizes may remain constant or
may vary
Assesses only two possible outcomes
for an event
Subgroup size to detect an out of control
event
Subgroup frequency to detect changes
in process
REFERENCE
Image Credits
Dugdale, D. (2010). Analyzing financial data [Online image]. Retrieved October 7, 2015 from
https://www.flickr.com/photos/davedugdale/5099605109/
OPERATIONS MANAGEMENT

with Gopesh Anand

MODULE 4
Quality Management
Lesson 4-2
Variability Assessment
Video 4-2.4
Attribute Data Control Charts
Count Data
EXAMPLE: DEFECTS IN FABRIC

A textiles manufacturer wants to determine the quality level of the

current weaving process for fabric used to make women’s shirts.
The process supervisor takes daily samples of 5 linear yards of
material and counts the number of flaws using a magnifying glass
to inspect the fabric.
She has collected data for 20 days.
Please check whether the process is under statistical control, and if
it is, report the number of defects that should ordinarily be expected
from the current process.
SAMPLES OF 5 LINEAR YARDS OVER 20 DAYS

Day Number Number of Flaws Day Number Number of Flaws

1 11 13
9
2 12 8
6
3 13 11
18
4 14 4
11
5 15 7
10
6 16 9
8
7 17 5
12
8 18 12
11
9 19 9
17
10 20 10
14
LET’S DO THE NUMBERS

(Dugdale, 2010)
C CHART

Central Line = C

Upper Control Limit : C + 3 C

Lower Control Limit : C - 3 C

C CHART CENTER LINE AND CONTROL LIMITS
Center line for control chart:
Total number of errors
÷
Total number of equal sized samples
= 204 ÷ 20 = 10.2
Standard deviation = Sq. root { c } = 10.2 = 3.19
UCL and LCL
= 10.2 ± 3 * 3.19 = (0.63, 19.77)
As in the case of P charts, if the computed lower control limit is negative,
change to 0, as counts of defects cannot be negative.
C CHART

C Chart of Defects in Fabric

20 UCL=19.78

15
Sample Count

_
10 C=10.2

LCL=0.62
0
1 3 5 7 9 11 13 15 17 19
Sample

Output from Minitab® Software

INTERPRETATION

The current process is expected to

produce between 1 and 19 defects.

Less than 1 and greater than 19

defects in 5 yards is an indication of
possible special causes.
Figure out root causes of higher defects.
Figure out reasons behind exceptional
performance.
USE OF C CHART

Multiple opportunities for defects or

imperfections in a given unit
Each unit is an area of opportunity.
Each area of opportunity is a subgroup.
Areas of opportunity are of constant
size
REFERENCE
Image Credits
Dugdale, D. (2010). Analyzing financial data [Online image]. Retrieved October 7, 2015 from
https://www.flickr.com/photos/davedugdale/5099605109/
OPERATIONS MANAGEMENT

with Gopesh Anand

MODULE 4
Quality Management
Lesson 4-2
Variability Assessment
Video 4-2.5
Variable Data Control Charts
VARIABLE CONTROL
CHARTS, IN GENERAL

Used to study process characteristics

that are measurements, e.g., height,
area, temperature, cost, weight, or
time
Used in pairs
With one chart studying variation in a process,
while the other studies process average

Chart that studies process average

assumes that process variability is
stable over time
EXAMPLE: TEMPERATURE OF AMERICANOS
Holly, a barista at Mercury Coffee House, prides herself on the precision of
her process for making cold milky Americanos that retains all the flavor of
the coffee while cooling it down in controlled stages.
She builds each drink using an elaborate process that involves brewing
espresso in cold stainless steel cups, transferring two shots into a glass
cup, and adding cold milk that is maintained in a refrigerator set to 34
degrees Fahrenheit (0 degrees Celsius).
Holly wants to assess the consistency of the temperature of the
Americanos that she serves and has collected data over the last 5 days,
using samples of the first four Americanos from the 12 noon to 1 pm hour
each day.
TEMPERATURE OF
AMERICANOS
Observation

Sample 1 2 3 4

1 35.12 35.09 35.06 35.07

2 35.03 35.1 35.11 35.08

3 35.14 35.09 35.13 35.12

4 35.08 35.05 35.11 35.01

5 35.06 35.09 35.14 35.11

LET’S DO THE NUMBERS

(Dugdale, 2010)
AVERAGE OF SAMPLE AVERAGES AND RANGES

Observation Calculations

Sample 1 2 3 4 Average Range

1 35.12 35.09 35.06 35.07

2 35.08 35.05 35.11 35.01

3 35.03 35.1 35.11 35.08

4 35.06 35.09 35.14 35.11

5 35.14 35.09 35.13 35.12

Average
AVERAGE OF SAMPLE AVERAGES AND RANGES

Observation Calculations

Sample 1 2 3 4 Average Range

1 35.12 35.09 35.06 35.07 35.085 0.06

2 35.08 35.05 35.11 35.01 35.063 0.1

3 35.03 35.1 35.11 35.08 35.08 0.08

4 35.06 35.09 35.14 35.11 35.1 0.08

5 35.14 35.09 35.13 35.12 35.12 0.05

Average 35.0895 0.074

X BAR - R CHART
CONTROL CHART CONSTANTS FOR 3 STANDARD
DEVIATIONS
Factor Factor Factor Factor
Sample Factor Sample Factor
for LCL for UCL for LCL for UCL
Size for X-bar Size for X-bar
for R for R for R for R
(n) (A2) (n) (A2)
(D3) (D4) (D3) (D4)
2 1.880 0 3.267 10 0.308 0.223 1.777
3 1.023 0 2.574 12 0.266 0.284 1.716
4 0.729 0 2.282 14 0.235 0.329 1.671
5 0.577 0 2.114 16 0.212 0.364 1.636
6 0.483 0 2.004 18 0.194 0.392 1.608
7 0.419 0.076 1.924 20 0.180 0.414 1.586
8 0.373 0.136 1.864 22 0.167 0.434 1.566
9 0.337 0.184 1.816 24 0.157 0.452 1.548
R CHART CENTER LINE
AND CONTROL LIMITS

Center Line
Mean of Ranges = 0.074
Upper Control Limit
D4 * Mean Range
= 2.282 * 0.074 = 0.1689
Lower Control Limit
D3 * Mean Range
= 0.00 * 0.074 = 0.000
X BAR CHART CENTER
LINE AND CONTROL LIMITS

Center Line
Mean of Means = 35.0895

Upper Control Limit

Mean of Means + A2 * Mean of Ranges
= 35.0895 + 0.73 * 0.074 = 35.1435

Lower Control Limit

Mean of Means - A2 * Mean of Ranges
= 35.0895 - 0.73 * 0.074 = 35.0355
X BAR - R CHART

Xbar-R Chart of Cold Americano Temperature

35.150
U C L=35.1434

35.125
Sample M ean

35.100 _
_
X=35.0895
35.075

35.050
LC L=35.0356
1 2 3 4 5
Sample

U C L=0.1688
0.16
Sample Range

0.12

_
0.08 R=0.074

0.04

0.00 LC L=0
1 2 3 4 5
Sample

Output from Minitab® Software

INTERPRETATION

Holly’s Americanos are served at a

pretty consistent temperature.
Temperatures vary a maximum of 0.1688
degrees Fahrenheit.
Temperatures are expected to be
between 35.0356 and 35.1434 degrees
Fahrenheit.
However
What is the customer’s expectation?
REFERENCE
Image Credits
Dugdale, D. (2010). Analyzing financial data [Online image]. Retrieved October 7, 2015 from
https://www.flickr.com/photos/davedugdale/5099605109/
OPERATIONS MANAGEMENT

with Gopesh Anand

MODULE 4
Quality Management
Lesson 4-2
Variability Assessment
Video 4-2.6
Process Capability
PROCESS CAPABILITY

Ability of the process to meet the

design specifications for a service or
product

Specifications provided by the

process customer in the form of
tolerances:
Upper and lower specification limits
APPLICABILITY OF PROCESS
CAPABILITY ANALYSIS

Measurement data

Normal distribution

Statistical control established

PROCESS CAPABILITY RATIO, CP

Definition
Potential for process to be consistent enough to be
within customer tolerance
Computation
Tolerance width divided by 6 standard deviations

Upper specification − Lower specification

Cp =
6*s
Interpretation
Ratio smaller than one signifies process is not capable
of producing output within customer specs
UNDERLYING BASIS:
NORMAL DISTRIBUTION

µ = Population Mean σ = Standard Deviation

(Kernler, 2014)
INTUITION FOR PROCESS
CAPABILITY RATIO, CP
PROCESS CAPABILITY INDEX, CPK

Potential for process to generate defective outputs

relative to upper or lower specifications

x= – Lower specification =
Upper specification – x
Cpk = Minimum of ,
3*s 3*s

Take the minimum of the two ratios. Cpk indicates how

process is positioned in relation to specifications (also
called tolerances).
INTUITION FOR PROCESS
CAPABILITY INDEX, CPK
EXAMPLE: EXPEDITED ORDERS

A restaurant on the “magnificent mile” in Chicago promises quick lunch

meals of high quality from a limited menu and with some customization.

Market research has determined that office-going and tourist customers

expect their somewhat customized orders to take between 2 and 16
minutes from order to arrival of food at the table.

Their current process has an average turnaround time from order to arrival
of food at the table of 12 minutes and a standard deviation of 2 minutes.

Is the process capable of conforming to customer expectations about

lunch order turnaround time?
LET’S DO THE NUMBERS

(Dugdale, 2010)
PROCESS CAPABILITY RATIO, CP

Upper specification limit (USL) = 16 minutes

Lower specification limit (LSL) = 2 minutes

Average service time = 12 minutes

Standard deviation of service times (s) = 2 minutes
16 – 2
Cp = = 1.17
(6 * 2)
Interpretation: Process has potential of being capable
PROCESS CAPABILITY INDEX, CPK
Upper specification limit (USL) = 16 minutes
Lower specification limit (LSL) = 2 minutes

Average service time = 12 minutes

Standard deviation of service times (s) = 2 minutes
= – Lower specification
x Upper specification – =
x
Cpk = Minimum of ,
3s 3s
Cpk = Minimum of 12 – 2 , 16 – 12
(3 * 2) (3 * 2)
= Minimum of 1.67, 0.67 = 0.67
Interpretation: Process not capable; mean is too far to the right
OVERALL INTERPRETATION AND POSSIBLE
ACTION

Variability in the process is low enough for possibly fulfilling

customer expectations

Average time of 12 minutes is too high

Compare to the center of the customer tolerance range
Center point between 2 and 16 is 9 minutes

Reducing the standard deviation (e.g., to 1) would also make

process capable

Combination of reducing mean and standard deviation

A PROCESS IS CAPABLE
WHEN …
… both the process capability ratio (Cp)
and the process capability index (Cpk) are
at least 1.
PICTURING A CAPABLE
PROCESS
PICTURING A NON-
CAPABLE PROCESS
IN-VIDEO QUESTION 6
(1 OF 2)

Interpret the four situations depicted

in the schematics relating customer
specifications and process
performances.

For each situation, consider whether

process capability ratio and process
capability index will be 1 or greater.
IN-VIDEO QUESTION 6
(2 OF 2)

(a) (b)
Customer specification Customer specification

Process distribution Process distribution

(c) (d)
Customer specification Customer specification

Process distribution Process distribution

IN-VIDEO QUESTION 6
(2 OF 2)

(a) (b)
Customer specification Customer specification

Process distribution Process distribution

(c) (d)
Customer specification Customer specification

Process distribution Process distribution

(flickr.com/taymazvalley, 2010)
IN-VIDEO INSIGHT 6

(a) (b)
Customer specification Customer specification

Process distribution Process distribution

(c) (d)
Customer specification Customer specification

Process distribution Process distribution

APPLICABILITY TO ONE-
SIDED SPECIFICATIONS

Examples:
Minimum expected time of delivery is 0
Only higher limit of roughness for cloth is
concern for customer
EXAMPLE: ONLY MAXIMUM
TIME SPECIFIED

Fast food customers expect orders

to arrive in less than 3 minutes.
The current process at Leslie’s
Burgers delivers orders in an
average time of 1 minute and a
standard deviation of 0.5 minutes.
Is the process capable of
conforming to customer
expectations about lunch order
turnaround time?
LET’S DO THE NUMBERS

(Dugdale, 2010)
FAST FOOD ORDER TURNAROUND
ASSESSING PROCESS CAPABILITY
Upper specification limit (USL) = 3 minutes
Lower specification limit (LSL) = 0 minutes
Average service time = 1 minute
Standard deviation of service times (s) = 0.5 minute
Cp = Undefined

Cpk = Upper specification – x= =

3–1
= 1.33
3s (3 * 0.5)

Interpretation: Process is capable of fulfilling customer expectations of order

turnaround time.
IN GENERAL, USES OF PROCESS CAPABILITY
ASSESSMENT

Quick indicators of the chances of fulfilling and failing process

customer requirements

Comparison across different processes and suppliers

Supplier cost calculations

Effective tracking and communication tool for buyer-supplier

communications
(Linn, Tsung, & Ellis, 2006)
REFERENCE
Academic Citations
Linn, R. J., Tsung, F., & Ellis, L. W. C. (2006). Supplier selection based on process capability and price analysis. Quality
Engineering, 18(2), 123-129. doi: 10.1080/08982110600567475

Image Credits
Dugdale, D. (2010). Analyzing financial data [Online image]. Retrieved October 7, 2015 from
https://www.flickr.com/photos/davedugdale/5099605109/
Kernler, D. (2014). Empirical rule [Online image]. Retrieved October 7, 2015 from
https://commons.wikimedia.org/wiki/File:Empirical_Rule.PNG
Valley, T. (2010). Think [Online image]. Retrieved October 7, 2015 from
https://www.flickr.com/photos/taymazvalley/5209251530/
OPERATIONS MANAGEMENT

with Gopesh Anand

MODULE 4
Quality Management
Lesson 4-2
Variability Assessment
Video 4-2.7
Lesson Recap
LESSON 4-2 RECAP

In this lesson you learned how to:

Distinguish between common cause and
special cause variation.
Use SPC to assess routine performance
level of processes.
Recognize occurrences of special cause
variation.
Compare routine process performance to
customer expectations.