Most of the hypothesis testing procedure [ eg.

, t-test, z-test, annova etc ] are based on the assumption that

the samples are selected from normal population. They are known as Parametric methods as they depend
on the parameters, viz., mean or proportion or standard deviation or covariation etc. These paametric tests
have used the parametric statistic of sample that comes from the population being tested.
But the Non-parametric test do not require the population to be normal. They even apply to nonnumerical data.They are also called as distribution free methods.
ADVANTAGES OF NON PARAMETRIC OVER PARAMETRIC METHODS:
1.
2.
3.
4.
5.
6.
7.

They can be used to test population parameters when the variable is not normally distributed.
They can be used when the data are nominal or ordinal.
They can be used to test the hypothesis that do not involve population parameters.
In most cases the computation are more easier than those for the parametric counterparts.
They are easy to understand, quicker and easier to apply when the sample sizes are small.
They are less time consuming.
They make fewer and lesser stringent assumptions.

DISADVANTAGES OF NON PARAMETRIC OVER PARAMETRIC METHODS:

1. They are less sensitive than their parametric counterparts when the assumption of the parametric
methods are met. Therefore large differences are needed before the null hypothesis can be
rejected.
2. They tend to use less information than the parametric tests. For example the sign test requires the
researchers to determine only whether the data values are above or below the median, not how
much below or above the median each value is.
3. They are less efficient than their parametric counterparts when the assumptions of parametric
methods are met. i.e., the larger sample sizes are nedded to over come the loss of information.
Efficiency of Nonparametric Methods

TYPES OF NON PARAMETRIC TEST:

NON-PARAMETRIC TEST
1.Sign Test:
One Sample Test
Paired Sign Test
2.Rank Test/U-Test/ Man-Whitney
U-test

FORMULAE

Z=

; Where

3.Kruskal-wallis (or) H- Test

4.Run Test

Z=
Where

Where

= Expected frequency;

5.Kolmogrov-Smirnov Test
frquency
6.Co-varience

Cov(x,y)=

=Observed