Chapter-13: Analysis of Variance Techniques

CHAPTER-13
ANALYSIS OF VARIANCE TECHNIQUES

SLIDE 13-1
What is ANOVA?
•The test of hypothesis concerning the
equality of two population means makes use
of both the Z and t tests.
•However, if there are more than two
populations, the test for the equality of
means could be carried out by considering
two populations at a time. This would be a
very cumbersome procedure.
•One easy way out could be to use the
analysis of variance (ANOVA) technique. The
SLIDE 13-2
What is ANOVA?
•The basic principle underlying the technique
is that the total variation in the dependent
variable is broken into two parts—one which
can be attributed to some specific causes and
the other that may be attributed to chance.
•The one which is attributed to the specific
causes is called the variation between
samples and the one which is attributed to
chance is termed as the variation within
samples.
SLIDE 13-3
What is ANOVA?
•In ANOVA, the dependent variable in
question is metric (interval or ratio scale),
whereas the independent variables are
categorical (nominal scale).
•If there is one independent variable (one
factor) divided into various categories, we
have one-way or one-factor analysis of
variance.
•In the two-way or two-factor analysis of
variance, two factors each divided into the
SLIDE 13-4
Completely Randomized Design

in a One-way ANOVA
•In this design, there is one dependent variable and one
independent variable.
•The dependent variable is metric (interval/ratio scale)
whereas the independent variable is categorical (nominal
scale).
•A sample is drawn at random from each category of the
independent variable.
•The size of the sample from each category could be equal or
different.
SLIDE 13-5

in a One-way ANOVA
•The total variation in the data set is called the total sum of squares (TSS)
and is computed as:
Where,
xij = the jth observation of the ith sample
T•• = Grand total of all the data
k = Number of treatments (samples)
n = Number of observations in each sample
SLIDE 13-6

in a One-way ANOVA
•The variation between the sample means which is attributed to specific
sources or causes is referred to as the treatment sum of squares (TrSS).
Where, Ti• = Total of observations for the ith treatment.
The variation within the sample, which is attributed to chance, is

referred to as the error sum of squares (SSE).
SLIDE 13-7

in a One-way ANOVA
In order to test the null hypothesis,
H0 : μA = μB = μC = μD
against the alternative hypothesis
H1 : At least two means are not equal
(Treatment means are not equal)
The results could be summarized in the table below called One-way ANOVA.
SLIDE 13-8

in a One-way ANOVA
•For a given level of significance, α, the computed F statistic is compared
with the table value of F with k – 1 degrees of freedom in the numerator
and k (n – 1) degrees of the freedom for the denominator. If the
computed F value is greater than the tabulated F value, the null
hypothesis is rejected.
Case of Unequal Sample Size from Treatments

•If there are ni observations corresponding to ith treatment, the
computing formula for the sum of squares would look like:
SLIDE 13-9

in a One-way ANOVA
SSE = TSS – TrSS
Where, N = n1 + n2 + . . . . + nk
The total number of degrees of freedom in the case is N – 1, and the
degrees of freedom are k – 1 for the treatments and N – k for the error.
The ANOVA table can be set up with the above information and if
computed F is greater than the table value of F, null hypothesis could be
rejected.
SLIDE 13-10
Randomized Block Design in

Two-way ANOVA
•The main limitation of the completely
randomized design is that all extraneous
variables were assumed to be constant over
all the treatment groups which may not be
true.
•There may be extraneous variables
influencing the dependent variable.
•In the randomized block design it is possible
to separate the influence of one extraneous
variable on a particular dependent variable,
SLIDE 13-11

Two-way ANOVA
•Assume that the sales of a product is influenced not only by the price
level (low, medium and high) but also by the size of the stores. The price
level is assumed to be independent variable whereas the size of the
stores are extraneous variable and could be treated as different blocks.
•The hypothesis to be tested are the following:
I Price
H0 : μA = μB = μC (Assuming three price level)
H1 : At least the two means are not same.
II (Blocks or Stores)
H0 : ν1 = ν2 = ν3 (Assuming three different sizes of stores)
H1 : At least two means are not same.
SLIDE 13-12

Two-way ANOVA
•The total sum of squares (TSS) and treatment sum of squares (TrSS)
could be computed as discussed in completely randomized design. Now,
we would also have another component called block sum of squares
(SSB) which is due to different store sizes and is computed as:
Where, T•j = Total of the values in the jth block.

The error sum of squares would be computed as:
SSE = TSS – TrSS – SSB
SLIDE 13-13

Two-way ANOVA
•The above results could be presented in a two-way ANOVA table as
below:
For a given level of significance, the computed F corresponding to

treatments and blocks could be compared with the corresponding
tabulated values to accept of reject the two hypothesis.
SLIDE 13-14
Factorial Design
•In factorial design, the dependent variable is
the interval or the ratio scale and there are
two or more independent variables which are
nominal scale.
•It is possible to examine the interaction
between the variables. If there are two
independent variables, each having three
cells, there would be a total of nine
interactions.
•The hypothesis to be tested would be the
SLIDE 13-15
Factorial Design
Row-wise:
H0 : Average of rows are equal.
H1 : Average of rows are not equal
Column-wise:
H0 : Average of columns are equal.
H1 : Average of columns are not equal
Interaction:
H0 : Average of all interactions between rows and columns are equal.
H1 : Average of all interactions between rows and columns are not equal
SLIDE 13-16
Factorial Design
•Total sum of squares (TSS), sum of squares due to rows (SSR) & sum of
squares due to columns (SSC) can be computed as explained earlier. We
also need to compute sum of squares due to interaction (SSI).
• Sum of squares due to error (SSE) can be computed as :

SSE = TSS – SSR – SSC – SSI
SLIDE 13-17
Factorial Design
•The ANOVA table for factorial design can be

computed in the usual manner to test the
various hypothesis stated earlier using F
statistic.
SLIDE 13-18
Latin Square Design

The Latin square design has three important characteristics:
1. The number of categories must be equal for the two
extraneous (control) variables.
2. The number of experimental (treatment) groups should
equal to the numbers of categories in the control variables.
3. Each experimental (treatment) group must appear only
once in every row and column.
SLIDE 13-19
Latin Square Design

•Assuming that we are interested in studying the impact of the price
categorized as low (A), medium (B) and high (C). Two extraneous
variables, namely, the store size and the type of packaging, could also
influence sales.
•The layout of the Latin square design for this problem could be as shown
in the table below:
SLIDE 13-20
Latin Square Design

•The hypothesis to be tested is:
H0 : All the treatments (price levels have an equal effect on sales.
H1 : All the price levels do not have equal effect on sales.
We need to compute the following:
SLIDE 13-21
Latin Square Design
•The ANOVA table for Latin square design could be set up as shown in the
next slide.
SLIDE 13-22
Latin Square Design
For a given level of significance, the computed F statistic corresponding

to treatment is compared with the tabulated value to accept or reject the
null hypothesis.
END OF CHAPTER

Chapter-13: Analysis of Variance Techniques

Uploaded by

Copyright:

Available Formats

Chapter-13: Analysis of Variance Techniques

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Chapter-13: Analysis of Variance Techniques

Uploaded by

Copyright:

Available Formats

CHAPTER-13

ANALYSIS OF VARIANCE TECHNIQUES

Completely Randomized Design

Completely Randomized Design

Completely Randomized Design

Where, Ti• = Total of observations for the ith treatment.

The variation within the sample, which is attributed to chance, is

Completely Randomized Design

Completely Randomized Design

Case of Unequal Sample Size from Treatments

Completely Randomized Design

Randomized Block Design in

Randomized Block Design in

Randomized Block Design in

Where, T•j = Total of the values in the jth block.

Randomized Block Design in

For a given level of significance, the computed F corresponding to

• Sum of squares due to error (SSE) can be computed as :

•The ANOVA table for factorial design can be

Latin Square Design

Latin Square Design

Latin Square Design

Latin Square Design

Latin Square Design

For a given level of significance, the computed F statistic corresponding

You might also like