Scribd
Upload
57 views

Introduction to Factorial Designs (Thiết kế giai thừa)

1. The document introduces factorial designs, which involve experiments with all possible combinations of factor levels. Factorial designs allow investigation of main effects and interactions between factors. 2. A two-factor factorial design is presented, with examples of calculating main effects and interactions. An ANOVA table is shown for analyzing the results of a two-factor fixed effects design. 3. Both quantitative and qualitative factors are discussed. Response curves and surfaces can be used to model and interpret results when experiments include both types of factors.

Uploaded by

Dan ARik
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
57 views

Introduction to Factorial Designs (Thiết kế giai thừa)

1. The document introduces factorial designs, which involve experiments with all possible combinations of factor levels. Factorial designs allow investigation of main effects and interactions between factors. 2. A two-factor factorial design is presented, with examples of calculating main effects and interactions. An ANOVA table is shown for analyzing the results of a two-factor fixed effects design. 3. Both quantitative and qualitative factors are discussed. Response curves and surfaces can be used to model and interpret results when experiments include both types of factors.

Uploaded by

Dan ARik
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 29

Design and Analysis

of Experiments

Chapter 5

Introduction to
Factorial Designs
(Thiết kế giai thừa)
Dr. Tran Thanh Hung
Department of Automation Technology,
College of Engineering, Can Tho University
Email: [email protected]
Chapter objectives

At the end of this chapter, students can:


• know the concept and principles of
factorial designs
• use ANOVA to analyse two-factors
factorial designs
Contents

• General principles of factorial designs


• The two-factor factorial with fixed
effects
• The ANOVA for factorial designs
• Quantitative and qualitative factors –
response curves and surfaces
• Extensions to more than two factors

3
Basic Definitions

• Factorial design = experiments with all


possible combinations of the levels of the
factors are investigated
Ex: Factor A has a levels, Factor B has b levels
 ab treatment combinations/1 replicate
• Main effect of a factor = the change in
response produced by a change in the level of
the factor
Basic Definitions

Main effect / factor effect = The change in the mean response when the factor
is changed from low to high
Calculation of the main effect of:
40  52 20  30
A  y A  y A    21
2 2
30  52 20  40
B  yB   yB    11
2 2
52  20 30  40
AB    1  no interaction between 2 factors 5
2 2
The Case of Interaction

50  12 20  40
A  y A  y A   1
2 2
40  12 20  50
B  yB   yB     9
2 2
12  20 40  50
AB    29  interaction is large! 6
2 2
Regression Model

How to illustrate the concept of interaction?

 Regression model representation of


the two-factor factorial experiment:

y   0  1 x1   2 x2  12 x1 x2   ,
where : y  response,
x1  factor A variable,
x2  factor B variable,
(x1 , x2 scaled in [-1 +1]  low to high levels) ,
x1 x2  interaction between x1and x2
  random error.
7
Regression Model & Response Surface

y   0  1 x1   2 x2  12 x1 x2  
1  (main effect of A) /2 =21/2,
 2  (main effect of B) /2=11/2,
12  (interaction beetween AB) / 2  1/ 2
 0  (20 + 40 + 30 + 52) / 4
 yˆ  35.5  10.5 x1  5.5 x2  0.5 x1 x2
 35.5  10.5 x1  5.5 x2

8
Effect of Interaction
on the Response Surface

Suppose that we add an interaction term to the model:

yˆ  35.5  10.5 x1  5.5 x2  8 x1 x2


Interaction is actually a form of curvature (đường cong)

60

50

40

-1
30

0
20
-1 -0.5 1
0 0.5 1 x2
x1 9
Two-Factor Factorial Design:
Example 5-1 (The Battery Life Experiment)

A = Material type; B = Temperature (A quantitative variable)


1. What effects do material type & temperature have on life?
2. Is there a choice of material that would give long life
regardless of temperature (a robust product)? 10
Two-Factor Factorial Design: General

a levels of factor A; b levels of factor B; n replicates


This is a completely randomized design (CRD) 11
Two-Factor Factorial Design: model

Statistical (effects) model:  i  1, 2,..., a



yijk     i   j  ( )ij   ijk  j  1, 2,..., b
k  1, 2,..., n

where:
 : overall mean effect,
 i : effect of the i th level of factor A,
 j : effect of the jth level of factor B,
( )ij : effect of the interaction between  i and  j ,
 ijk : random error,
a b
Assume:  =0,  
i 1
i
j 1
j =0, fixed case. 12

Other models (means model, regression models) can be useful


Two-Factor Factorial Design:
hypotheses
-Testing hypotheses about the equality of row treatment
effects:
H 0 : 1   2     a  0
H1 : at least one  i  0
-Testing hypotheses about the equality of column treatment
effects:
H 0 : 1   2     b  0
H1 : at least one  j  0
-Testing hypotheses about the row and column treatments
interaction:
H 0 : ( )ij  0 for all i, j
13
H1 : at least one ( )ij  0
Extension of the ANOVA to Factorials
yi.. : total of all observations under the i th level of factor A,
y. j . :total of all observations under the jth level of factor B,
yij . : total of all observations in the ijth cell,
y... : grand total of all the observations,
yi.. , y. j . , yij . , y... :corresponding row, column, cell, and grand averages,
b n
yi..
yi..   yijk , yi..  , i  1, 2,..., a
j 1 k 1 bn
a n y. j .
y. j .   yijk , y. j .  , j  1, 2,..., b
i 1 k 1 an
n yij .
yij .   yijk , yij .  , i  1, 2,..., a j  1, 2,..., b
k 1 n
a b n
y...
y...   yijk , y...  . 14
i 1 j 1 k 1 abn
Extension of the ANOVA to Factorials

The total corrected sum of squares: 2


a b n a b ( yi..  y... )  ( y. j .  y... )
n 
 ( yijk  y... )   
2

i 1 j 1 k 1   ( y  y  y  y )  ( y  y )

i 1 j 1 k 1  ij . i .. . j. ... ijk ij . 
a b
 bn ( yi..  y... )  an ( y. j .  y... ) 2
2

i 1 j 1
a b a b n
 n ( yij .  yi..  y. j .  y... ) 2   ( yijk  yij . ) 2
i 1 j 1 i 1 j 1 k 1

 SST  SS A  SS B  SS AB  SS E
Number of degrees of freedom:
abn  1  a  1  b  1  (a  1)(b  1)  ab(n  1) 15
ANOVA Table – Fixed Effects Case

• The reference distribution for F0 is the F distribution


• Reject the null hypothesis H0 if
For A : F0  F ,a 1,ab ( n 1) For B : F0  F ,b 1,ab ( n 1)
16
For AB : F0  F , a 1  b 1 ,ab ( n 1)
Example 5-1: ANOVA output

17
Example 5-1: ANOVA output

F0.05,2,27  3.35  Reject H 0 for A, B


F0.05,4,27  2.73  Reject H 0 for AB

18
Residual Analysis – Example 5-1

19
Residual Analysis – Example 5-1

20
Quantitative / Qualitative Factors
(Yếu tố định lượng/định tính)
• The basic ANOVA procedure treats every factor as if
it were quantitative
• Sometimes an experiment will involve both
quantitative and qualitative factors, such as in
Example 5-1
• This can be accounted for in the analysis to produce
regression models for the quantitative factors at
each level (or combination of levels) of the qualitative
factors
• These response curves and/or response surfaces
are often a considerable aid in practical interpretation
of the results
21
Quantitative / Qualitative Factors

22
Quantitative / Qualitative Factors

A = Material type Candidate model terms


B = Linear effect of Temperature from Design- Expert:
Intercept
B2 = Quadratic effect of Temperature
A
AB = Material type – TempLinear B
AB2 = Material type - TempQuad B2
AB
B3 = Cubic effect of Temperature B3
(Aliased) AB2

23
Regression Model Summary of
Results

24
Regression Model Summary of
Results

25
Factorials with More Than
Two Factors

• Basic procedure is similar to the two-factor


case; all abc…kn treatment combinations are
run in random order
• ANOVA identity is also similar:
SST  SS A  SS B    SS AB  SS AC  
 SS ABC    SS ABK  SS E

• Complete three-factor example in text, Example


5-5
26
Three-factor analysis of variance
Thực hành chương 5

• Bài 1: Dùng Minitab phân tích kết quả thí


nghiệm trong ví dụ 5-1
Số liệu kết quả thí nghiệm:
Thực hành chương 5

• Bài 2: Xếp máy bay giấy với 2 yếu tố,


mỗi yếu tố thay đổi 3 mức. Phóng thử
mỗi loại 10 lần, ghi lại độ xa mỗi lần
phóng. Dùng Minitab phân tích kết quả.

You might also like