MATH 50 – ENGINEERING
DATA ANALYSIS
Chapter 10. Design of
Experiments with Several
Factors
Engr. Roxanne Joy R. Opelac
Mariano Marcos State University
College of Engineering
Department of Agricultural and Biosystems Engineering
OUTLINE
1. Factorial Experiments
2. Two-Way ANOVA for Two Factor Experiments
3. General Factorial Experiments
4. 2k Factorial Design
a. 22 Design
b. 2k Design for k 3 Factors
Introduction
• An experiment is a test or series of tests.
• The design of an experiment plays a major role in
the eventual solution of the problem.
• In a factorial experimental design, experimental
trials (or runs) are performed at all combinations of
the factor levels.
• The analysis of variance (ANOVA) will be used
as one of the primary tools for statistical data
analysis.
Factorial Experiments
• By a factorial experiment we mean that in each complete
trial or replicate of the experiment all possible combinations
of the levels of the factors are investigated.
A Factorial Experiment with
A Factorial Experiment with Two Factors
Interaction
Factorial Experiments
Factorial Experiment, no Factorial Experiment, with
interaction interaction
A Factorial Experiment with A Factorial Experiment with
Two Factors Interaction
TWO-FACTOR FACTORIAL EXPERIMENTS
Data Arrangement for a Two-Factor Factorial Design
TWO-FACTOR FACTORIAL EXPERIMENTS
Statistical Analysis of the Fixed-Effects
Model
Statistical Analysis of the Fixed-Effects
Model
Statistical Analysis of the Fixed-Effects
Model
Computing formulas for the sums of squares in
a two-factor analysis of variance.
ANOVA Table for a Two-Factor Factorial,
Fixed-Effects Model
• F Test for Factor A
Reject Ho
• F Test for Factor B
Reject Ho
• F Test for AB Interaction
Reject Ho
Example
Aircraft primer paints are applied to aluminum surfaces by two
methods: dipping and spraying. A factorial experiment was performed
to investigate the effect of paint primer type and application method
on paint adhesion. For each combination of primer type and
application method, three specimens were painted, then a finish paint
was applied, and the adhesion force was measured. The data from the
experiment are shown in the table. The circled numbers in the cells
are the cell totals yij. . . The experimenter has decided to use =0.05.
Analyze the data using ANOVA.
Source of Sum of Degrees of Mean F0
Variation Squares Freedom Square
Primer Types 4.58 2 2.29 28.63
Application
4.91 1 4.91 61.38
Methods
Interaction 0.24 2 0.12 1.50
Error 0.99 12 0.08
Total 10.72 17
Source of Sum of Degrees of Mean Square F0
Variation Squares Freedom
Primer Types 4.58 2 2.29 28.63
Application
4.91 1 4.91 61.38
Methods
Interaction 0.24 2 0.12 1.50
Error 0.99 12 0.08
Total 10.72 17
Since f =3.89 and f
0.05,2,12 =4.75, we conclude that
0.05,1,12
the main effects of primer type and application
method affect adhesion force. Furthermore, since
1.5 < f = 3.89, there is no indication of
0.05,2,12
interaction between these factors.
General Factorial Experiments
Analysis of Variance Table for the Three-Factor Fixed
Effects Model
2k Factorial Designs
• Factorial designs are frequently used in experiments involving several
factors where it is necessary to study the joint effect of the factors on a
response.
• 2 – is the number of levels
• k – is the number of variables
• The most important of these special cases is that of k factors, each at
only two levels. These levels may be quantitative, such as two values
of temperature, pressure, or time; or they may be qualitative, such as
two machines, two operators, the “high’’ and “low’’ levels of a factor,
or perhaps the presence and absence of a factor.
22 Design
• Simplest type of 2k design – two factors A and B, each at two levels
22 Design
• The main effect of Factor A is estimated by:
1
𝐴= [𝑎 + 𝑎𝑏 − 𝑏 − 𝑙]
2𝑛
• The main effect of Factor B is estimated by:
1
𝐵= [𝑏 + 𝑎𝑏 − 𝑎 − 𝑙]
2𝑛
22 Design
• The interaction effect is estimated by
1
𝐴𝐵 = [𝑎𝑏 + 𝑙 − 𝑎 − 𝑏]
2𝑛
• The quantities in brackets in the 3 equations are
called contrasts. For example, the A contrast is
22 Design
• In these equations, the contrast coefficients are always either
+1 or -1. The table can be used to determine the sign on
each treatment combination for a particular contrast.
Signs for
effects in
the 22
Design
1 1
𝐴= [𝑎 + 𝑎𝑏 − 𝑏 − 𝑙] 𝐵= [𝑏 + 𝑎𝑏 − 𝑎 − 𝑙]
2𝑛 2𝑛
22 Design
• Contrasts are used in calculating both the effect estimates
and the sums of squares for A, B, and the AB interaction.
• For any 2k design with n replicates, the effect estimates are
computed from
𝐶𝑜𝑛𝑡𝑟𝑎𝑠𝑡
𝐸𝑓𝑓𝑒𝑐𝑡 =
𝑛2𝑘−1
and the sum of squares for any effect is
𝐶𝑜𝑛𝑡𝑟𝑎𝑠𝑡 2
𝑆𝑆 =
𝑛2𝑘
22 Design
• For 22 Design, the sums of squares formulas are
𝑎 + 𝑎𝑏 − 𝑏 − 𝑙 2
𝑆𝑆𝐴 =
4𝑛
𝑏 + 𝑎𝑏 − 𝑎 − 𝑙 2
𝑆𝑆𝐵 =
4𝑛
𝑎𝑏 + 𝑙 − 𝑎 − 𝑏 2
𝑆𝑆𝐴𝐵 =
4𝑛
An article describes the application of two-level factorial designs to
integrated circuit manufacturing. A basic processing step in this
industry is to grow an epitaxial layer on polished silicon wafers.
The table below presents the results of a 22 factorial design
with n=4 replicates using the factors A deposition time and B arsenic
flow rate. The two levels of deposition time are short and long, and
the two levels of arsenic flow rate are 55% and 59%. The response
variable is epitaxial layer thickness (m). Estimate the factor effects
and confirm these effects by the analysis of variance.
Source of Sum of Degrees of Mean F0
Variation Squares Freedom Square
A (deposition 2.7956 1 2.7956 134.40
time)
B (arsenic 0.0181 1 0.0181 0.87
flow)
AB 0.0040 1 0.0040 0.19
Error 0.2495 12 0.0208
Total 3.0672 15
2k Design for k 3 Factors
2k Design for k
3 Factors
2k Design for k 3 Factors
2k Design for k 3 Factors
Main Effect of Factor A
Main Effect of Factor B
Main Effect of Factor C
2k Design for k 3 Factors
Two-Factor Interaction Effect
Three-Factor Interaction Effect
Consider the surface roughness experiment with observed data
tabulated below. This is a 23 factorial design in the factors feed
rate (A), depth of cut (B), and tool angle (C), with n=2
replicates.
ANOVA
Source of Sum of Degrees of Mean F0 P-Value
Variation Squares Freedom Square
A 45.5625 1 45.5625 18.69
B 10.5625 1 10.5625 4.33
C 3.0625 1 3.0625 1.26
AB 7.5625 1 7.5625 3.10
AC 0.0625 1 0.0625 0.03
BC 1.5625 1 1.5625 0.64
ABC 5.0625 1 5.0625 2.08
Error 19.5000 8 2.4375
Total 92.9375 15
References
Montgomory, DC and GC Runger. 2014. Applied
Statistics and Probability for Engineers. 6th
Edition. John Wiley & Sons Inc. USA. 836 pp.
Get in Touch
With Us
Send us a message or
visit us
City of Batac, Ilocos Norte,
Philippines
(63) 77-600-0459
op@mmsu.edu.ph
Follow us for updates
facebook.com/MMSUofficial
www.mmsu.edu.ph
