Morning Session (Day 1)

• Why are 1, 2, 3, 4 and 5 Sigma inferior to 6 Sigma?
• What is Sigma?
• Is 10 Sigma better quality than 6 Sigma?
• Why stop at 6 Sigma?
• The 4 Basic Measures of Variability
• How is Sigma related to quality?
• The Spirit of Six Sigma & Taguchi Loss Function
• How many Sigma can you place within a given tolerance?
• If you can only place 3 Sigma, what does it mean?
• If you can only place 6 Sigma, what does it mean?

Afternoon Session

• Defects per million concept
• Why minimize the variation first before centering the mean?
• SPC language of Six Sigma
• Business Language of Six Sigma
• Layman language of Six Sigma
• Definition of Cp and Cpk
• Tolerance and Quality
• Six Sigma Quality

Tutorial:

a) How to calculate Cp and Cpk?
b) How to calculate Sigma?

Projects Identification (optional)

Summary of Day 1

Morning Session (Day 2)

• DMADV in detail
• Design of Experiments Roadmap - 15 Step Process
• Financial or Technical Reasons for DOE
• The nature of business
• Business Gravitational Forces
• The Six Sigma Quality: Value Added Cost without any Waste
• The three important questions every staff needs to ask
• Tolerance and Yield
• The Concept of Process Entitlement
• What can Design Of Experiments do for you?
• What is Accuracy? What is Precision?
• Causes of Variation: Special and Common causes
• Process Average and Variation
• The biggest headache is when the common causes can no longer be tolerated
• Sources of Variability in Product Quality
• Potential Areas for Variability Reduction
• Objectives of DOE

Afternoon Session

• Individual Participation: On Target No Variation (scenario 1, 2, 3 and 4)
• Higher Quality Implies Variance Reduction Around the Target
• Explore the factors that deliver a product that is on target with low variation and low cost
• DOE Must Be Financially Viable
• The Rich Dad Poor Dad Perspectives of Problem Solving and Opportunity Seeking
• When not to apply DMAIC?
• Theory of Constraints and the Weakest Link

Tutorial: 3-5 and 3-12 ( Completely Randomized Design)

To be in business, you have to answer two fundamental questions with a certain degree of confidence. Can you?

Group Participation: Which is normal? The danger of ‘ Normal Mentality’.

Projects Identification (optional)

Summary of Day 2

Morning Session (Day 3)

• The prerequisite to conduct a Design of Experiment
• One Single Data can cause you to make a wrong decision

Illustration: 'Now you REJECT and Now you ACCEPT'

• Assignable Cause will distort your judgment
• Hypothesis Testing and Alternative Hypothesis
• The Three Assumptions of ANOVA
• Normal Distribution
• The Concept of Total Variation, The Concept of Within Variation, The Concept of Between Variation
• Using Bar Chart to reveal the amount of variation in the data set
• ANOVA Table: Sum of Squares, Degree of Freedom, Mean Squares and F-Ratio
• Sum of Squares and its Additivity Property
• Differences between Vertical and Horizontal Blocking
• Why Analysis of Variance (ANOVA)?
• The Power of ANOVA (decompose or partition of total variation into its respective factors/interactions/error)
• The relationship of between variation and assignable/special causes
• The relationship of within variation and common/random causes

Afternoon Session

• F distribution, F-Ratio and F-Table
• Why use Microsoft Excel for Design of Experiments Calculation?
• The Power of Microsoft Excel Library Function
• Completely Randomized Design is The Base Design (the beginning)
• The scalable ANONA Table
• The similarity in ANOVA Table removes the fear in DOE
• Best Practices in Design of Experiments

Tutorial A: 5-1, 5-2, 5-7 ( Randomized Complete Block Design)

Tutorial B: 5-14 ( Latin Square Design) ; 6-1, 6-4, 6-6, 6-7 (Two-Factor Factorial Design)

Identification of Potential Root Causes of Variation and Lowest Total Cost Option

Projects Identification (optional) & Projects Review

Summary of Day 3

Morning Session (Day 4)

• What needs to improve? What went wrong?
• Role of DOE in Process Improvement
• Conducting Good Experiment

1. Choice of factors, including their range;

• Knowledge of what the results are applicable to; and
• Choice of experimental materials, procedure, and equipment.
• Choosing the Number of Factors
• Choosing the Levels for Each Factor
• What is your confidence level in factors selection and levels setting?
• The three basic principles of Design of Experiments are:
• Replication,
• Randomization and,
• Blocking

Afternoon Session

• DOE Terminology
• Which model is suitable to your process: Fixed Effects Model or Random Effects Model?
• Planning a DOE
• How to select the amount of replication?
• The importance of randomizing the order of the tests
• Trial Number; Treatment Number; Setting Number
• Treatment Combination; Setting Condition
• The meaning of Complete Randomization, Simple Repetitions, and Blocking
• How to randomize?
• Why without confirmation run, DOE is only a prediction tool?
• Business Considerations: Profitability and Customer Repurchase Intention
• Do Your Customers Count Sigmas?
• Examples of data collection forms for the various classical DOEs and Taguchi Designs

Tutorial A: 7-1, 7-5, 7-15 ( 2 K Factorial Design)

Tutorial A: 2 IV 4-1, 2 IV 6-2, 2 IV 7-3 ( 2-Level Fractional Factorial Design)

In-door experiential learning activities related to the application of the DOE concepts learned.

Projects Review (optional)

Summary of Day 4

Morning Session (Day 5)

• Important features of 2 K Factorial Design
• 2 K Factorial Design: first-order effects, two-factor interactions, three-factor interactions, four-factor interactions, five-factor interactions
• Differences between Full Factorial Experiment, 1/2 Fractional Factorial Experiment, 1/4 Fractional Factorial Experiment, 1/8 Fractional Factorial Experiment
• Fractional Factorial Design Resolution
• Resolution III design, Resolution IV design, Resolution V design: Resolution IV classification is of main interest
• The Sparsity of Effects Principle
• What is Aliases or Confounding?

Illustration: Forcing a 2 4 Factorial Design into a 2 3 Factorial Design

• Why you need to predetermine the two-factor interactions?
• How many two-factor interactions can you study in Fractional Factorial Design?
• Revisit the Concept of Blocking

Afternoon Session

• What is the Taguchi Method?
• What is the Quality Loss Function?
• What is Robust Design?
• What is the Signal-to-Noise Ratio (S/N)?
• What are Orthogonal Arrays?
• What are the three goals in Taguchi parameter design?
• The main advantages of Taguchi Methods
• What are the Common Orthogonal Arrays?
• The 3 distinct Signal to Noise Ratios: Nominal-is-Best; Smaller-is-Better; Larger-is-Better

Tutorial: L 4(2 3), L 8(2 7), L 9(3 4) { Taguchi Method (L 4, L 8, L 9)}

Examples of Aliases / Confounding

Case Study; Food for Thought – 1, 2, 3

Projects Review (optional)