Improving Performance Using
Statistical Thinking
MN ASQ Section 1203
post-Dinner Meeting
September 14, 1999
presented by Robert Mitchell
Chair, ASQ Statistics Division
MISSION
Promote Statistical Thinking for quality and productivity
improvement.
Serve ASQ, business, industry, academia, and government as a
resource for effective use of Statistical Thinking for quality and
productivity improvement.
Our primary customers are Statistics Division members.
Other key customers are:
Management
Users and potential users of Statistical Thinking
Educators of the above customers
Provide a focal point within ASQ for application-driven
development and effective use of new statistical methods.
Support the growth and development of ASQ Statistics Division
members.
VISION
Statistical Thinking Everywhere
Statistical Thinking Statistical Methods
Process Variation Data Improvement
Philosophy Analysis Action
DESIRED END STATE
Our members will be proud to be part of the Statistics
Division
Our Division’s operations will be a model for other
organizations.
We will be a widely influential authority on scientific
approaches to quality and productivity improvement.
PRINCIPLES
Our customers’ needs will be continuously anticipated
and met (i.e. Customer focused rather than customer
driven).
Our market focus for products and services is
weighted as follows:
Greatest weight on intermediate level
Nearly as much weight on basic level
Much less weight on advanced level.
Focus on a few key things.
Balance short-term and long-term efforts.
Value diversity (including geographical and
occupational) of our membership.
Be proactive.
PRINCIPLES
Recognize that we exist for our customers.
View statistics from the broad perspective of quality
management.
Apply Statistical Thinking ourselves; that is, practice
what we preach.
Uphold professional ethics.
Continuously improve.
STRATEGY
Design and deliver selected useable products.
Have a strong and vibrant Division infrastructure.
Demonstrate the broad effectiveness of Statistical Thinking.
Integrate Statistical Thinking into educational curricula.
Develop a vibrant information communication system.
Influence key decision makers.
Improving Performance Through
Statistical Thinking
• Why ST is important?
• What is ST?
• How do you apply ST?
• How to begin implementing ST
capability in an organization
• Summary
• Appendix - tools, case studies
Definition
Statistical Thinking is a philosophy of learning and
action based on the following fundamental principles:
All work occurs in a system of interconnected
processes
Variation exists in all processes
Understanding and reducing variation are keys
to success.
Glossary and Tables for Statistical Quality Control - Quality Press, 1996
Evaluation Based on Past Experiences
or Perceptions
We’ve always done it this way!
We work with what we get!
We do the best we can!
I never thought about it!
I’m so busy with the day to day troubles, I
don’t have time
to try that!
That has no effect on the finished product
(or service)!
Evaluation Based on Data
THE KEY IS TO ASK WHY!!!
Why is the material from the fabrication
department machine so inconsistent?
Why do so we constantly firefight?
Why does our daily output vary so much?
Why does every job result in a monumental
task that takes forever to complete?
Definition
Statistical Thinking is a philosophy of learning and
action based on the following fundamental principles:
All work occurs in a system of interconnected
processes,
Process
Transforms Inputs into Outputs
Inputs Transformation Outputs
Suppliers Accounts Payable Finished
Information Car Repair Goods
Historical Data Blending or Services
Approvals
External Factors
- Materials - People
- Methods - Machines
- Environment - Measures
Processes and Sub-Processes
Supplier Supplier Supplier Supplier
External External
Sub- Sub- Sub-
Supplier Customer
Process A Process B Process C
Customer Customer Customer Customer
Definition
Statistical Thinking is a philosophy of learning and
action based on the following fundamental principles:
All work occurs in a system of interconnected
processes
Variation exists in all processes
Like it or not, variation is everywhere!
Our drive time to work each day.
The quantity of production each shift.
Departure time of our plane.
Measurement system
………
Know it, accept it, learn to deal with it!
Definition
Statistical Thinking is a philosophy of learning and
action based on the following fundamental principles:
All work occurs in a system of interconnected
processes
Variation exists in all processes
Understanding and reducing variation are keys
to success.
Deming once said:
“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.”
Variation and Targets
Variation can be thought of as:
1. Deviations around the overall
average or
Ave
2. A deviation of the overall average
from a desired target.
Ave Target
Reduced deviation around the
Average and on Target
Voice of Voice of
Process Customer
Target
Improvement
using
Statistical Thinking
Process Variation Data Improvement
Statistical Thinking Statistical Methods
Philosophy Analysis Action
Pitfall
Valuing only quantitative data
Qualitative data are just as important.
Example: Idea data!!
Benefits of Statistical Thinking
Provides a theory and methodology for improvement:
Helps identify where improvement is needed.
Provides a general approach to take.
Suggests tools to use.
A complete improvement approach includes all
elements of Statistical Thinking:
Process - Variation - Data
Tips for Statistical Thinking
CAPDo Diagnostic
Check
Act
Assess major problems and
Fix the obvious.
root causes
Decide how to
Define the scope of the project
Identify the people who will approach the
be affected by the project issue or
problem.
Do Plan
Implement the Check Act
Set project goals
plan. and expectations.
Assure continued Develop the
Do Plan
process project plan.
performance.
Use of Statistical Thinking
Depends on levels of activity and job responsibility.
Where we're
Strategic Executives
headed
Systems & processes
Managerial Managers
to guide us
Where the work
Operational Workers
gets done
Process
Process
Inputs Outputs
Suppliers Customers
S I P O C
A series of activities that converts inputs into outputs
Understand Customer Needs
Substitute Tech. Char. Product Planning Matrix
End
User
Req.. Mfg. Tests Qualification Matrix
Data
Converting Package
Cu Matrix
st
Pr om
oc er Coating
es Re
s/ qu
Pr ire
od m
uc en
tF ts Extruding
lo
w
Examples of Operational Processes
Manufacturing
Order Entry
Delivery
Distribution
Billing
Collection
Service
Examples of Statistical Thinking
at the Operational Level
Work processes are flowcharted and
documented
Key measurements are identified.
Time series plots displayed
Process management and improvement utilize:
Knowledge of variation, and
Data
Improvement activities focus on the process,
not blaming employees.
Examples of Managerial Processes
1. Employee Selection 6. Setting Objectives
2. Training and and Goals
Development 7. Project
3. Performance Management
Management 8. Communications
(including coaching)
9. Management
4. Recognition and Reporting
Reward
10. Planning
5. Budgeting
Examples of Managerial Processes
Management
Employee Reporting Training &
Selection Development
Planning
Core Business Processes
Objectives
& Goals
Budgeting
Customers
Communication Recognition
& Rewards
Performance
Management
Examples of Statistical Thinking
at the Managerial Level
Managers use meeting management techniques
Standardized project management systems are
in place.
Both project process and results are reviewed.
Process variation is considered when setting
goals.
Measurement is viewed as a process.
.
The number of suppliers is reduced
A variety of communication media are used.
Examples of Strategic Processes
Strategic Plan Development
Strategic Plan Deployment
Acquisitions
Corporate Budget Development
Communications - Internal and
External
Succession Planning and Deployment
Organizational Improvement
Examples of Statistical Thinking
at the Strategic Level
Executives use systems approach.
Core processes have been flow charted
Strategic direction defined and deployed.
Measurement systems in place (i.e. BSC).
Employee, customer, and benchmarking
studies are used to drive improvement.
Experimentation is encouraged.
Learning is valued.
Robustness - An Underused Concept
Key aspect of Statistical Thinking
Reduce the effects of uncontrollable
variation in:
Product design
Process design
Management practices
Anticipate variation and reduce its effects
Robustness of Product and Process
Design
A third way to reduce variation
Anticipate variation
Design the process or product to be insensitive to
variation
A robust process or product is more likely to
perform as expected
Improved reliability
100% inspection cannot provide robustness
Robust Products are Designed in
Anticipation of Customer Use
Unintended Use
Washing machine tops
Craftsman tools
User-friendly computers and software
Low-maintenance automobiles
5 mph bumpers
Medical instruments for home use
Product and Process Robustness
Product Performance is insensitive to
variations in conditions of manufacture,
distribution, use and disposal.
Process Performance is insensitive to
uncontrollable variation in process
Inputs
Transformations - activities - steps
External factors
Robustness in Management
Develop strategies that are insensitive to
economic trends and cycles
Scenario Planning
Design a project system that is insensitive to
Personnel changes
Changes in project scope
Variations in business conditions
Respond to differing employee needs
Adopt flexible work hours
Provide “cafeteria” benefits package
More ...
Robustness in Management
(Continued)
Enable personnel to adapt to changing
business needs
High Performance Organization (HPO)
Change Acceleration Process (CAP)
Technological Acceptance
Cultural Acceptance
Ensure meeting effectiveness is not dependent
on facilities, equipment, or participants
Understanding Human Behavior
Different people have different methods and
styles of working, learning and thinking
Different people take in, process and
communicate information in different ways
People vary --- they are different:
Day to day
Person to person
Group to group
Site to site
Organization to organization
Process Robustness Analysis
Identify Those Uncontrollable Factors that
Affect Process Performance
Weather
Customer Use of Products
Employee Knowledge, Skills, Experience, Work
Habit
Age of Equipment
Design the Process to be Insensitive to the
Uncontrollable Variations in the Factors
Three Ways to Reduce Variation
and Improve Quality
Control the Process:
Eliminate Special
Cause Variation
Improve the System: Quality
Reduce Common Improvement
Cause Variation
Anticipate Variation:
Design Robust
Processes and Products
Tips for Statistical Thinking
Start with the customer.
Identify customer requirements and
expectations. Identify market trends.
Start small.
Pick a process that is not very detailed and does
not involve many functions or work groups.
Small “wins” build confidence and teamwork.
Share successes; celebrate failures.
Tips for Statistical Thinking
7 Quality Tools 7 Management Tools
• Flow Diagram • Affinity Diagram
• Pareto Charts • InterRelationship
• Cause & Effect Diagram
• • Tree Diagram
Histograms
• • Prioritization Matrices
Run Charts
• • Matrix Charts
Control Charts
• • Arrow Diagram
Scatter Diagram
• Process Decision
Program Chart
3 Types of Variation
Special Cause
Common Cause
Structural
Identify Process State
Threshold State
Process StatesIdeal State
Process in Control Process in Control
NonConformance 100% Conforming
Change process or Product
specs Maintain Control
Sort
State of Chaos Brink of Chaos
Out of Control Out of Control
Out of Spec 100% Conforming
Eliminate Special Investigate Special
Causes Causes
Tips for Statistical Thinking
If a process or system is not stable -- showing signs
of Special Cause …
Use the tools of problem-solving to identify the root
cause. Try to identify exactly when, where, how, and
why the process changed.
If a Special Cause hurts the process, develop
procedures to eliminate the return of the problem. If a
Special Cause is beneficial, develop procedures to make
it a permanent part of the process.
Tips for Statistical Thinking
If a process or system is stable -- showing only
Common Causes of variation…
Use the tools of improvement to study all the data
(not just the “good” or the “bad” points) and
identify factors that cause variation. Determine
what needs to be permanently changed to achieve a
different level of quality.
Stratify the process - sort the data into groups
Disagregate the process - divide the process into its sub-
processes
Kano Model of Quality
Satisfied
Requested
Quality
Fulfilled
Not Fulfilled
Expected
Quality
Not Satisfied
Statistical Thinking Everywhere
1999 - 2000 STAT Tactics
1. Demonstrate the Broad Application of Statistical Thinking D1
Collect new case studies; Market Statistical Thinking
Expand the theory of Statistical Thinking
Assist in the discovery process for new applications
Maintain the integrity of ST (license and trademark)
Publish new series, “Improving Processes…”
2. Integrate Statistical Thinking into Education & Training B2
Pilot the “Pegasus” charter school project (Dallas, TX)
PDCA the process; repeat with new school principals
3. Develop a Vibrant Information & Communication System A2
Develop and implement a member nurturing process
Create and staff the Section Liaison position
Develop a WebPages policy and e-commerce strategy
4. Design & Deliver Selected Useable Products B5
Develop and disseminate Newsletter technical content
Create a Clearinghouse of Statistical Stuff
Beef-up our Short Course offerings; more variety; regional
Identify and start no more than 3 new publications
5. Have a Strong and Vibrant Division Infrastructure C3
Division organization re-alignment; change By-Laws
Develop a Division “Balanced Scorecard”
Statistical Thinking Everywhere
read more about it...
“Statistical Thinking” Special Publication (Spring 1996)
“Data Sanity” Special Publication (Summer 1998)
available through QIC 1-800-248-1946 or qic@[Link]
“How to Teach Others to Apply Statistical Thinking”
Quality Progress, June 1997, pg. 67 - 79
“Improving Performance through Statistical Thinking”
ASQ Quality Press available November 1999