Design and Analysis

of Experiments

Chapter 6

The 2 Factorial Design

k

Dr. Tran Thanh Hung

Department of Automation Technology,
College of Engineering, Can Tho University
Email: tthung@ctu.edu.vn
 Chapter objectives

At the end of this chapter, students can:

• Understand the idea of 2-level Factorial
Designs as one of the most important
screening designs
• Can design and analysis 2-level Factorial
Designs.
 Introduction: 2k Factorial Design
• Special case of the general factorial design; k
factors, all at two levels
• The two levels are usually called low and high
(they could be either quantitative or qualitative)
• Very widely used in industrial experimentation
Too many factors!
Which is the most important?
• Assumptions:
• - Fixed factors
• - Completely randomized design
• - Normality distribution
The Simplest Case: The 22 Design

“-” and “+” denote the

low and high levels of
a factor, respectively
Low and high are
arbitrary terms
Geometrically, the four
runs form the corners
of a square
Factors can be
quantitative or
qualitative, although
their treatment in the
final model will be
different
Example: Chemical Process

Note:
(1): treatment at A- and B-
a: treatment at A+ and B-
b: treatment at B+ and A-
ab: treatment at A+ and B+
 Analysis Procedure for a
Factorial Design
• Estimate factor effects
• Formulate model
– With replication, use full model
– With an unreplicated design, use normal
probability plots
• Statistical testing (ANOVA)
• Refine the model
• Analyze residuals (graphical)
• Interpret results
 Estimation of Factor Effects
Main effect of A
ab  a b  (1)
A  y A  y A  
2n 2n
1
 [ab  a  b  (1)]
2n   contrast
  
A

Main effect of B
ab  b a  (1)
B  yB  yB  
2n 2n
1
 [ab  b  a  (1)]
2n   contrast
  
B The effect estimates are:
Interaction effect: A = 8.33, B = -5.00, AB = 1.67
Practical interpretation?
ab  (1) a  b 1
AB    [ ab  (1)  a  b]
2n 2n 2n   contrast
   
AB
 Determining the sums of squares
Sum of square of A :
1
SS A  [ab  a  b  (1)]2
4n   contrast
  
A

Sum of square of B :
1
SS B  [ab  b  a  (1)]2
4n   contrast
  
B

Sum of square of interaction:

1
SS AB  [ab  (1)  a  b]2
4n   contrast
   
AB

Total sum of squares:

2 2 n 2 2 n 2
y
SST   ( yijk  y... ) 2   yijk 2
 ...
i 1 j 1 k 1 i 1 j 1 k 1 4n
SS E  SST  SS A  SS B  SS AB
 Estimation of Factor Effects
Form Tentative Model

Term Effect SumSqr % Contribution

Model Intercept
Model A 8.33333 208.333 64.4995
Model B -5 75 23.2198
Model AB 1.66667 8.33333 2.57998
Error Lack Of Fit 0 0
Error P Error 31.3333 9.70072
 Statistical Testing - ANOVA

The F-test for the “model” source is testing the significance of the
overall model; that is, is either A, B, or AB or some combination of
these effects important?
 Regression Model

Regression model :
y   0  1 x1   2 x2  12 x1 x2   ,
8.33
1  (main effect of A) /2 =
2
5
 2  (main effect of B) /2=
2
1.67
12  (interaction AB) / 2 
2
 0  ((1) + a + b + ab) / 4n
x1 , x2 are scaled in [-1 +1]  [low high] 8.33 5
 yˆ  27.5  x1  x2
2 2
11
 Regression Model for the Process

Coefficient Standard 95% CI 95% CI

Factor Estimate DF Error Low High VIF
Intercept 27.5 1 0.60604 26.12904 28.87096
A-Concentration
4.166667 1 0.60604 2.79571 5.537623 1
B-Catalyst -2.5 1 0.60604 -3.87096 -1.12904 1

Final Equation in Terms of Coded Factors:

y =
27.5
4.166667 * A
-2.5 * B

Final Equation in Terms of Actual Factors:

y =
18.33333
0.833333 * Concentration
-5 * Catalyst
Residuals and Diagnostic
Checking
The Response Surface
The 23 Factorial Design
Effects in The 23 Factorial Design

A  y A  y A
B  yB   yB 
C  yC   yC 
etc, etc, ...
Example 6.1: wafers manufacturing

(Công cụ khắc plasma)

Example 6.1: Wafer plasma etching

(sccm: standard cubic centimeter per

minute)
 Table of – and + Signs for the 23
Factorial Design

1
Effect of A  [(1)  a  b  ab  c  ac  bc  abc]
4n
1
Effect of B  [(1)  a  b  ab  c  ac  bc  abc], n :number of replicates
4n
 Properties of the Table
• Except for column I, every column has an equal number of +
and – signs
• The sum of the product of signs in any two columns is zero
• Multiplying any column by I leaves that column unchanged
(identity element)
• The product of any two columns yields a column in the table:

A  B  AB
AB  BC  AB 2C  AC
• Orthogonal design
• Orthogonality is an important property shared by all factorial
designs
Estimation of Factor Effects
ANOVA Summary – Full Model
Model Coefficients – Full Model
Refine Model – Remove Nonsignificant
Factors
Model Coefficients – Reduced
Model
The Regression Model
Response surface and contour plot
Model Summary Statistics for
Reduced Model
 Model Summary Statistics for
Reduced Model
• R2 and adjusted R2 (Đánh giá độ chính xác của mô
hình)
SS 5.106  10 5
R 2  Model   0.9608
SST 5.314 10 5

SS E / DFE 20857.75 /12

R 2
Adj  1  1  0.9509
SST / DFT 5.314 10 /15
5

• PRESS 37080.44
2R2 for prediction (based on PRESS: PRediction Error Sum
R Pred  1  1  0.9302
SS T 5.314 10
of Squares) (Đánh giá độ chính xác dự5 đoán giá trị mới)
The General 2k Factorial Design
The General 2k Factorial Design

 k  k  k  1   k  i  1
 
i i  i  1 1
 Thực hành chương 6

• Bài 1: Dùng Minitab phân tích kết quả thí

nghiệm trong ví dụ 6.1
Số liệu kết quả thí nghiệm: