ANALYSIS OF

VARIANCE
(ANOVA)
CONTENT
Analysis of Variance: Purpose
and Procedure

One-Way ANOVA

Two-Way ANOVA
OBJECTIVE
After completing this chapter you should be able to

Explain the purpose of ANOVA

Identify the assumptions that underlie the ANOVA technique

Describe the ANOVA hypothesis testing procedure

Use the one-way ANOVA technique to determine if there is a
significance difference among three or more means

Use the two-way ANOVA technique to determine if there is an
effect of interaction between two factors experiment

6.1 Analysis of Variance:
Purpose and Procedure
ANOVA
the approach that allows us to use sample data to see if the values
of three or more unknown population means are likely to be different
Also known as factorial experiments
this name is derived from the fact that in order to test for statistical
significance between means, we are actually comparing (i.e.,
analyzing) variances.

Example of problems
A manager want to evaluate the performance of three (or more)
employees to see if any performance different from others
A marketing executive want to see if theres a difference in sales
productivity in the 5 company region
A teacher wants to see if theres a difference in students
performance if he use 3 or more approach to teach.
The Procedural Steps for an
ANOVA Test
1. State the Null and Alternative
hypothesis
2. Select the level of significance
3. Determine the test distribution to use
4. Define rejection or critical region
5. State the decision rule
6. Compute the test statistic
7. Make the statistical decision
6.2 One-Way ANOVA
Only one classification factor is considered
Factor

Treatment
1
2
i
(The level of
the factor)
Response/ outcome/
dependent variable
(samples)
Replicates (1,,j)
The object to a
given treatment
The resulting input grid of
factorial experiment
where,

i = 1, 2, a is the number of levels being tested.
j = 1, 2, is the number of replicates at each level.

Assumptions
To use the one-way ANOVA test, the following assumptions
must be true

The population under study have normal distribution

The samples are drawn randomly, and each sample is
independent of the other samples.

All the populations from which the samples values are
obtained, have the same unknown population variance, that
is for k number of populations,
2 2 2
1 2 k
o o o = = =
The Null and Alternative
hypothesis
1 2
:
o k
H = = =
(All population means are equal)

1
: for
i j
H i j = =
(Not all population means are equal)

2 2 2
1 2 1 2
and
k k
o o o = = = = = =
If Ho is true we have k number of normal populations with
2 2 2
1 2 3 1 2 3
but o o o = = = =
If H1 is true we may have 3 normal populations with
The format of a general
one-way ANOVA table
2 2
..
1 1
1
k n
ij
i j
SST x T
kn
= =
=

2
/
( )
( )
1
Treatment Factor
MS Tr
SS Tr
k
o =
=

2
/
2
test
Treatment Factor
Error
F
o
o
=
2
Error
SSE
MSE
N k
o = =

Degrees
of
Freedom
(Df)
Sum of Squares (SS) Mean of Squares (MS) F Value
Between
sample
(Factor
Variation)



k -1
Within
samples
(Error
variation)


T- k



Total


T-1

( ) SSE SST SS Tr =
2 2
. ..
1
1 1
( )
k
i
i
SS Tr T T
n kn
=
=

Reject H
o
if , 1, test k T k
F F
o
>
T = kn
Example 1
The data shows the Maths test score for 4 group of
student with 3 different methods of study. Test the
hypothesis that theres no difference between the Maths
score at significance level 0.05.
Score
Individually &
Group study

80

70

85

89
Group study 60 55 58 62
Individually 65 60 62 58
Example 2
An experiment was performed to determine whether the
annealing temperature of ductile iron affects its tensile strength.
Five specimens were annealed at each of four temperatures. The
tensile strength (in ksi) was measured for each temperature. The
results are presented in the following table. Can you conclude
that there are differences among the mean strengths?
Temperature
(
o
C)
Sample Values
750 19.72 20.88 19.63 18.68 17.89
800 16.01 20.04 18.10 20.28 20.53
850 16.66 17.38 14.49 18.21 15.58
900 16.93 14.49 16.15 15.53 13.25
6.3 Two-Way ANOVA
Only two classification factor is considered
Factor B
1 2 j

Factor A
1
2
i
Assumptions
The standard two-way ANOVA tests are valid under the following
conditions:

The design must be complete
Observations are taken on every possible treatment

The design must be balanced
The number of replicates is the same for each treatment

The number of replicates per treatment, k must be at least 2

Within any treatment, the observations
are a simple random sample from a normal population

The sample observations are independent of each other (the samples
are not matched or paired in any way)

The population variance is the same for all treatments.
1
, ,
ij ijk
x x
The format of a general
two-way ANOVA table
2
2 ...
.
1 1
1
a b
ij
i j
x
SSAB x
n abn
= =
=

2
2 ...
. .
1
1
b
j
j
x
SSB x
an abn
=
=

2
Error
SSE
MSE
N k
o = =

2
2 ...
1 1 1
a b n
ijk
i j k
x
SST x
abn
= = =
=

( )( ) 1 1
SSAB
MSAB
a b
=

test
MSA
F
MSE
=
( )
1
SSE
MSE
ab n
=

SSE SST SSA

SSB SSAB
=

2
2 ...
..
1
1
a
i
i
x
SSA x
bn abn
=
=

1
SSA
MSA
a
=

1
SSB
MSB
b
=

test
MSB
F
MSE
=
test
MSAB
F
MSE
=
Source
(Df)
Sum of Squares (SS) Mean of Squares (MS) F Value

A

a - 1

B

b - 1

Interaction

(a-1)(b-1)

Error

ab(n-1)




Total

abn-1
Row
effect
Column
effect
Interaction
effect
Procedure for Two-Way ANOVA
START
Test for an interaction
between the two
factors
Is there an effect due
to interaction between the
two factors?
Stop. Dont consider the
effects of either factor
without considering the
effects of the other
Test for effect from
column factor
Test for effect from
row factor
Yes
(Reject Ho)
No (Accept Ho)
Ho: No interaction
between two factors
Ho: No effects from the
column factor (the column
means are equal)
Ho: No effects from the row
factor (the row means are
equal)
test
MSA
F
MSE
=
test
MSB
F
MSE
=
test
MSAB
F
MSE
=
Example 1
A chemical engineer is studying the effects of various reagents and
catalyst on the yield of a certain process. Yield is expressed as a
percentage of a theoretical maximum. 4 runs of the process were
made for each combination of 3 reagents and 4 catalysts. Construct
an ANOVA table and test is there an interaction effect between
reagents and catalyst.

Catalyst
Reagent
1 2 3
A 86.8 82.4
86.7 83.5
93.4 85.2
94.8 83.1
77.9 89.6
89.9 83.7
B 71.9 72.1
80.0 77.4
74.5 87.1
71.9 84.1
87.5 82.7
78.3 90.1
C 65.5 72.4
76.6 66.7
66.7 77.1
76.7 86.1
72.7 77.8
83.5 78.8
D 63.9 70.4
77.2 81.2
73.7 81.6
84.2 84.9
79.8 75.7
80.5 72.9
Example 2
A study was done to determine the effects of two factors on the
lather ability of soap. The two factors were type of water and
glycerol. The outcome measured was the amount of foam
produced in mL. The experiment was repeated 3 times for
each combination of factors. The result are presented in the
following table. Construct an ANOVA table and test is there an
interaction effect between factors.
Water type Glycerol Foam (mL)
De-ionized Absent 168 178 168
De-ionized Present 160 197 200
Tap Absent 152 142 142
Tap Present 139 160 160
Summary
The other name for ANOVA is
experimental design.
ANOVA help researchers to design an
experiment properly and analyzed the
data it produces in correctly way.
Thank You