Analysis-of-Variance Technique

In the estimation and hypothesis testing, we were restricted in each case

to considering no more than two population parameters.
To find out whether a new serum will arrest leukemia, 9 mice, all with an
advanced stage of the disease, are selected. Five mice receive the treatment and 4
do not. Survival times, in years, from the time the experiment commenced are as
follows:
Treatment 2.1 5.3 1.4 4.6 0.9
No Treatment 1.9 0.5 2.8 3.1

The survival time was measured for two samples of mice, where one
sample received a new serum for leukemia treatment and the other sample received
no treatment. In this case, we say that there is one factor, namely treatment, and
the factor is at two levels.
If several competing treatments were being used in the sampling process,
more samples of mice would be necessary. In this case, the problem would involve
one factor with more than two levels and thus more than two samples.
In the k > 2 sample problem, it will be assumed that there are k samples
from k populations. One very common procedure used to deal with testing
population means is called the analysis of variance, or ANOVA.
The analysis-of-variance approach is used to partition the total sum of
squares into a portion due to regression and a portion due to error.
Introduction
 In module 2, we learned the tests of hypotheses.
 One of them was testing equality of means of 2 populations.
 What if there are m different populations and we
wish to test the equality of means of them?
 One solution is to form {m Choose 2} (mC2) different
tests of hypotheses for each possible pair of 2 from m
populations.
 This is inefficient and uninformative
 A solution is to use a technique called “Analysis of
Variance” or ANOVA.
 A collection of statistical techniques and associated
procedures to compare equality of means by
splitting the overall observed variance in sample
data into different parts.
 It was pioneered by the British statistician and
geneticist R.A.Fisher in the 1920s and 1930s.
Some basic terminologies: