1

Introduction
Design of Experiment
Outline

2
Introduction
Introduction to DoX
●  An experiment is a test or a series of tests
●  All experiments are designed experiments, some are poorly
designed, some are well-designed
●  Experimentation is a vital part of scientific (or engineering)
method

Experiments are used widely in the engineering world:

○  Process characterization & optimization
○  Evaluation of material properties
○  Product design & development
○  Component & system tolerance determination
4
Introduction to DoX
For any experiment, questions to be asked:
•  Are only these methods available?
•  Are there any other factors that might affect the results?
•  How many samples are needed for the experiment?
•  How should the samples be assigned to each experiment?
•  What is the order that the data should be collected?
•  What method of data analysis should be used?
•  What difference in average observed results between method,
material, machines,…?

5
History of DoX (4 Eras)
●  The agricultural origins, 1918 – 1940s
○  W.S. Gossett and the t-test (1908)
○  R. A. Fisher & his co-workers
○  Profound impact on agricultural science
○  Factorial designs, ANOVA
●  The first industrial era, 1951 – late 1970s
○  Box & Wilson, response surfaces
○  Applications in the chemical & process industries
●  The second industrial era, late 1970s – 1990
○  Quality improvement initiatives in many companies
○  Taguchi and robust parameter design, process robustness
●  The modern era, beginning circa 1990
6
Engineering Experiments
Engineering Experiments
●  In general, experiments are used to study the
process and systems.
●  The process can be the combination of
operations, machines, methods, people, and
other resources (often materials) that transfer
some input into output that has one or more
observable response variables y.
●  Some of the process variables and material
properties, x1, …, xp are controllable.
●  Some of them are uncontrollable (although
they may be controllable for purposes of a
test).

8
Engineering Experiments
•  Determining which variables are most
influential on the response y
•  Determining where to set the influential x’s
so that y is almost always near the desired
nominal value.
•  Determining where to set the influential x’s
so that variability in y is small.
•  Determining where to set the influential x’s
so that the effects of the uncontrollable
variables z1, …., zq are minimized.

9
Typical Applications of
Experimental Design
●  Improve process yield
●  Reduce variability and closer conformance to
nominal or target requirements
●  Reduce development time
●  Reduce overall costs
●  Evaluate and compare basic design configurations
●  Evaluate material alternatives
●  Select design parameters
●  Determine key product design parameters
●  Formulate new product

10
Planning, Conducting, & Analyzing
an Experiment
1.  Recognition of & statement of problem
2.  Choice of factors, levels, and ranges Pre-experimental planning

3.  Selection of the response variable(s)

4.  Choice of design
5.  Conducting the experiment
6.  Statistical analysis
7.  Drawing conclusions, recommendations
8.  Get statistical thinking involved early
9.  Your non-statistical knowledge is crucial to success
10. Pre-experimental planning (steps 1-3) vital
11.  Think and experiment sequentially (use the KISS principle)
11
Randomization
○  Running the trials in an experiment in random order
○  Notion of balancing out effects of “lurking” variables

Replication
○  Sample size (improving precision of effect estimation,
estimation of error or background noise)

Blocking
○  Dealing with nuisance factors
The Basic
Principles of DoX
12
Strategy of Experimentation
Golf example-factor
to influence the
score
•  Driver – oversized or regular
•  Ball – balata or three piece
•  Mode of travel — walking or
riding a golf cart
•  Beverage – water or beer
•  …….
14
Strategy of
Experimentation
“Best-guess” One-factor-at-a-time Statistically designed
experiments (OFAT) experiments experiments
Used a lot Sometimes associated Based on Fisher’s factorial
More successful than you with the “scientific” or concept
might suspect, but there “engineering” method
are disadvantages Devastated by interaction,
also very inefficient

15
Strategy of Experimentation

16
Strategy of Experimentation

17
Factorial Design
Factorial Design
●  In a factorial experiment, all possible
combinations of factor levels are tested
●  The golf experiment:
○  Type of driver
○  Type of ball
○  Walking vs. riding
○  Type of beverage
○  Time of round
○  Weather
○  Type of golf spike
○  Etc.
19
20
Factorial Design

21
Factorial Design with
Several Factors

22
Factorial Design with Several Factors
A Fractional Factorial

23
Thanks!
Any questions?
You can find me at debrina@ub.ac.id & debrina.ub@gmail.com

24