Analysis of Variance (ANOVA)

Analysis of variance is the process of partitioning and discomposing total variation contained in
data into various independent components each of which is attributed to an identifiable causes or
source of variation and a further component due to chance faster. The analysis of variance
procedure of F-test is used in such problems where we want to test for the significance of the
difference among more than two sample means. In fact, the technique of analysis of variance is
one of the most powerful of statistical methods developed by R.A. Fisher. According to R.A.
Fisher-Analysis of variance is the separator of variance ascribable to one group of causes from
the variance ascribable to other group. ANOVA is a particular form of statistical hypothesis
testing heavily used in the analysis of experimental data. Before the use of ANOVA, the t-
test and z-test were commonly used. But the problem with the T -test is that it
cannot be applied for more than two groups.

Assumption in Analysis of Variance: The ANOVA technique is based on the following

assumption-

1) Each sample is drawn randomly from a normal population and the sample statistics
tend to reflect the characteristics of the population.
2) The populations from which the samples are drawn have identical means and
variance.

If we set the Type one error to be .05, and we have several groups, each time we
test a mean against another there would be a .05 probability of having a type one
error rate. This would mean that with six T -tests you would have a 0.30 (.056)
probability of having a type one error rate. This is much higher than the desired
.05.ANOVA creates a way to test several hypothesis at the same time.

Commonly there are 2 types of ANOVA. They are given below -

One-Way:

When we compare more than two groups, based on one factor, this is called one
way ANOVA. For example, it is used if a manufacturing company wants to
compare the productivity of three or more employees based on working hours.
This is called one way ANOVA.
One-way classification table;

Source of Variation Sum of Degrees of Mean Square F-ratio

Squares Freedom (df)
(SS) MS
Between samples SSB c-1 MSB=SSB/c-1

Within samples SSW n-c MSW=SSW/n- F=MSB/MSW

c
Total SST n-1

Two-Way:

When a company wants to compare the employee productivity based on two

factors, then it said to be two way ANOVA. For example, based on the working
hours and working conditions, if a company wants to compare employee
productivity, it can do that through two way ANOVA. Two -way ANOVAs can be
used to see the effect of one of the factors after controlling for the other, or it can
be used to see the INTERACTION between the two factors. This is a great way to
control for extraneous variables as you are able to add them to the design of the
study.

Two-way classification table;

Source of Variation Sum of Degrees of Mean Square F-ratio

Squares Freedom (df)
(SS) MS
Between columns SSC c-1 MSC=SSC/c-1 F=MSC/MSE

Between rows SSR r-1 MSR=SSR/r-1 F=MSB/MSW

Error SSE (c-1) (r-1) MSE=SSE/(c-

1) (r-1)
Total SST Rc-1