CHAPTER 3
GENERAL INTRO:
STATISTICAL DESIGN
OF EXPERIMENTS
Instructor: Lena Ahmadi
During
the
Lecture
E6-2004 Skype: L2ahm Ext.
Office L2ahm adi@u 37160
After Hour adi w...
the
Lecture
In Person Message Call
Course notes are copyrighted material. © Professor Alex Penlidis, 2019.
This copy is for individual use only in connection with this course.
It may not be resold or used to make additional copies.
Tel: (519) 888-4567 x36634, E-mail: penlidis@uwaterloo.ca
1
Major Topics
• Chapter 1:
Statistical Background
• Chapter 2:
Regression Analysis
• Chapter 3:
Statistical Design of Experiments
• Chapter 4:
Design/Analysis of Single Factor Experiments
• Chapter 5:
Blocking
• Chapter 6:
Multifactor Experiments
• Chapter 7:
Multifactor Experiments
• Chapter 8
Response Surface Methods/CCD
• Chapter 9:
Response Surface Methods/BBD,
Face Centered Designs, Nonlinear
Regression
• Chapter 10:
Data Transformations
• Chapter 11:
The Analysis of Undesigned Data,
• Chapter 12:
Concluding Remarks
2
Learning Objectives
• Learn about the objectives of
experimental design and the
role it plays in the knowledge
discovery process
• Learn about different strategies
of experimentation
• Understand the Nature of
Experimentation
3
GENERAL INTRO: STATISTICAL DESIGN OF
EXPERIMENTS
4
Source: https://athletics.uwaterloo.ca/sports
Remember 3 basic
keywords!
These keywords will be clarified in later
chapters and will be used throughout course
Randomize
Replicate
Block
WHY EXPERIMENTAL DESIGN?
1. Quality improvement.
2. Development of new products or
processes.
3. Troubleshooting of existing processes.
4. Optimize plant/process operation.
5. Learning about and understanding why a
process behaves the way it does.
WHY EXPERIMENTAL DESIGN?
Two approaches:
Informed but passive observation:
• someone who knows about the
process watches it change and tries
to deduce the cause.
• try to develop understanding from
historical (happenstance)
(undersigned) data.
Directed experimentation:
• someone who knows the process,
causes it to change in a systematic
fashion and watches the results of
those changes.
Iterative, Sequential Nature of
Experimentation
HYPOTHESIZE
DESIGN
ANALYZE
OBJECTIVE
NO MET?
YES
NO TENTATIVELY
OBJECTIVE ACCEPT
YES
CHANGED? RESULT
CAUTION
• Experimental design is not a black box
Problem Experimental Answer
Design
• You need to keep in mind the chemistry,
physics and engineering principles, as well
as statistics.
• Mechanistic vs empirical math models.
Experimental design procedures for avoiding the
problems that occur in the analysis of happenstance
data:
Problems in the analysis of Experimental design procedures
happenstance data for avoiding problem
1. Inconsistent data Blocking and Randomization
2. Range limited by control Experimenter makes own choice
of ranges for variables.
3. Semiconfounding of Use of designs such as factorials
effects that provide uncorrelated
estimates of the individual
effects.
4. Nonsense correlations Randomization
due to lurking variables
5. Serially correlated errors Randomization ( to some extent)
6. Dynamic relationships Where only steady-state
characteristics are of interest,
sufficient time is allowed
between successive runs for
process to settle down.
7. Feedback Temporary disconnection of
feedback system.
Concept Map
Why experimental design?
Hypothesis
General Intro:
Objective
Analyze
Design
Design/
Analysis of
Single Factor
Experiments
17
