NON

PARAMETRIC
STATISTICS
 Definition
Non-parametric tests
are the mathematical
methods used in
statistical hypothesis
testing, which do not
make assumptions about 3

the frequency distribution

3
 We will use NON PARAMETRIC
STATISTIC

• Whenever a few assumptions in the given

population are uncertain, we use non-
parametric tests, which are also considered
parametric counterparts.

• When data are not distributed normally or

when they are on an ordinal level of
measurement, we have to use non-
parametric tests for analysis
4

• The basic rule is to use a parametric t-test

5
Non-parametric Test Methods

Mann Whitney U Test

• Mann Whitney U test is used to
compare the continuous outcomes
in the two independent samples.

• Null hypothesis, H0: The two

populations should be equal.

• The alternative hypothesis (H1) is

that the two populations are not ●●●
equal. 9
When to use the Mann-Whitney
U Test
used when you want to compare two
independent groups on a single ordinal or
continuous outcome, especially when the data
does not meet the assumptions of normality
required for parametric tests like the t-test.
• Data is ordinal: The outcome variable is ranked or
ordered rather than measured on a continuous scale.
• Non-normal distribution: The data does not follow
a normal distribution.
• Unequal sample sizes: You have different numbers
of observations in each group.
• Presence of outliers: The data may contain outliers
that could influence parametric test results.
●●●
9
 Mann-Whitney U Test Example

The effectiveness of advertising for two rival

products (Brand X and Brand Y) was compared.
Market research at a local shopping centre was
carried out, with the participants being shown
adverts for two rival brands of coffee, which they
then rated on the overall likelihood of them buying
the product (out of 10, with 10 being "definitely
going to buy the product"). Half of the participants
gave ratings for one of the products, the other half
●●●
gave ratings for the other product. 9
 Mann-Whitney U Test Example

The effectiveness of advertising for two rival

products (Brand X and Brand Y) was compared.
Market research at a local shopping centre was
carried out, with the participants being shown
adverts for two rival brands of coffee, which they
then rated on the overall likelihood of them buying
the product (out of 10, with 10 being "definitely
going to buy the product"). Half of the participants
gave ratings for one of the products, the other half
●●●
gave ratings for the other product. 9
 The effectiveness of advertising for two rival
products (Brand X and Brand Y) was compared.
Market research at a local shopping centre was
carried out, with the participants being shown
adverts for two rival brands of coffee, which they
then rated on the overall likelihood of them buying
the product (out of 10, with 10 being "definitely
going to buy the product"). Half of the participants
gave ratings for one of the products, the other half
gave ratings for the other product.
STEP ONE:
Rank all scores together, ignoring which
group they belong to.
STEP ONE:
Rank all scores together, ignoring which
group they belong to.
STEP TWO
Add up the ranks for Brand X, to get T1

Therefore, T1 = 3 + 4 + 1.5 + 7.5 + 1.5 +

5.5 = 23

STEP THREE:
Add up the ranks for Brand Y, to get T2

Therefore, T2 = 11 + 9 + 5.5 + 12 + 7.5 +

10 = 55
STEP FOUR:

Select the larger rank. In this case it’s T2

T1 = 3 + 4 + 1.5 + 7.5 + 1.5 + 5.5 = 23

T2 = 11 + 9 + 5.5 + 12 + 7.5 + 10 = 55
STEP FIVE:

Calculate n1, n2 and nx These are the

number of participants in each group, and
the number of people in the group that
gave the larger rank total.
Therefore,
n1 = 6
n2 = 6
nx = 6
STEP SIX:
Find U
(Note: Tx is the larger rank total)
ADD THE TOTAL RANK OF BRAND X
AND BRAND Y

=2 =5
 STEP SEVEN:
Use a table of critical U values for the Mann-
Whitney U Test

For n1 = 6 and n2=6, the critical value

of U is 5 for a two-tailed test at the
0.05 significance level.
 STEP SEVEN:
Use a table of critical U values for the Mann-
Whitney U Test

For n1 = 6 and n2=6, the critical value

of U is 2 for a two-tailed test at the
0.01 significance level.
 STEP EIGHT:
To be significant, our obtained U has to be equal to or
LESS than this critical value.

• Our obtained U = 2 The critical value for a two

tailed test at .05 significance level = 5
• The critical value for a two tailed test at .01
significance level = 2

• So, our obtained U is less than the critical value of U

for a 0.05 significance level.

• It is also equal to the critical value of U for a 0.01

significance level.

• But what does this mean? We can say that there is

a highly significant difference (p<.01) between the
ratings given to each brand in terms of the
likelihood of buying the product.
Non-parametric Test Methods

Wilcoxon Signed-Rank Test

• Wilcoxon signed-rank test is used to
compare the continuous outcome in
the two matched samples or the
paired samples.

• Null hypothesis (H0): The median

difference should be zero.

• Alternative Hypothesis (H1): The

median difference is not zero.
When to use the Wilcoxon Signed
Ranked Test
use the Wilcoxon Signed-Rank Test when
comparing two related samples or
repeated measurements on a single
sample, especially when the data is not
normally distributed.
• Paired Data: You have two sets of related
data, like before-and-after measurements.

• Non-Normal Distribution: The differences

between pairs do not follow a normal
distribution.
Wilcoxon Signed Ranked Test
Example
A teacher wants to
evaluate the
effectiveness of a new
teaching method. They
measure the test scores
of 10 students before and
after using the new
method.
STEP ONE:
• Calculate the Difference: Subtract
the "After" score from the "Before"
score.
STEP TWO:
• Rank the Absolute Differences: Ignore the
signs and rank the absolute differences. If there
are ties, assign the average rank.
STEP THREE:
• Assign Signs to the Ranks: Assign the signs of
the original differences to the ranks.
STEP FOUR:
• Calculate the Test Statistic:
Sum the positive and negative
ranks separately.
Sum of positive
ranks:
(8.5 + 8.5 + 8.5 + 8.5 + 5 + 2.5 + 2.5 + 2.5 = 46.5)

Sum of negative
ranks:
(-2.5 - 5 = -7.5)

The test statistic (W) is the smaller of these two sums

which is (-7.5).
STEP FIVE:
• Determine the Critical Value: Use a
Wilcoxon Signed-Rank Test table to find the
critical value for (n = 10) at your chosen
significance level (e.g., 0.05).
For a Wilcoxon Signed-Rank Test with ( n
= 10 ) and a significance level of ( α =
0.05 ) (two-tailed), the critical value is 8.

This means that if your test statistic ( W ) is

less than or equal to 8, you would reject the
null hypothesis, indicating a statistically
significant difference between the paired
samples.
STEP SIX:

• Compare the Test Statistic to the

Critical Value: If the absolute value of
(W) is less than or equal to the critical
value, reject the null hypothesis.
Otherwise, do not reject the null
hypothesis.
Non-parametric Test Methods

Kruskal Wallis Test

• Kruskal Wallis test is used to compare
the continuous outcome in greater
than two independent samples.
• Null hypothesis, H0: K Population
medians are equal.
• Test statistic: If N is the total sample
size, k is the number of comparison
groups, Rj is the sum of the ranks in
the jth group and nj is the sample size
in the jth group, then the test statistic. ●●●
7
Non-parametric Test Methods

Chi-Square Test for independence

• The chi-square test for
independence, also called Pearson’s
chi-square test or the chi-square test
association, is used to test the
relationship between two categorical
variables.
Socioeconom
Presidential
ic
Bet
Status
●●●
7
Non-parametric Test Methods

Assumptions for Chi-square test for

independence
• The data in the cells should be frequencies,
or counts.
• There are 2 variables, and both are
measured as categories, usually at the
nominal level. However, data may be ordinal
data. Interval or ratio data that have been
collapsed into ordinal categories may also be
used.
• The value of the cell expected should be ●●●
5 or
7
Non-parametric Test Methods
Example: A ramen store wishes to determine
whether there is a difference in the level of
spiciness selected by males and females for their
ramen. A random sample provides the data given
below. At = 0.05, test the claim that the level of
spiciness selected is dependent to the gender of
the individual .

The spiciness level selected by an individual is independent

of the gender of the individual.
: The spiciness level selected by an individual is dependent
of the gender of the individual. (claim) ●●●
7
Non-parametric Test Methods
Chi- Square Test
Value ( 0 − 𝐸 ) 2
Expected value = 𝑥 =∑
2
𝐸

Where: ∑ = summation
O = observed value
E = expected value

Degrees of freedom
d.f. = (rows – 1)(columns – 1)

●●●
7
Non-parametric Test Methods
Chi- Square Test
Value ( 0 − 𝐸 ) 2
Expected value = 𝑥 =∑
2
𝐸

Where: ∑ = summation
O = observed value
E = expected value

Degrees of freedom
d.f. = (rows – 1)(columns – 1)

●●●
7
Non-parametric Test Methods
Chi- Square Test
2
Value
Expected value = 𝑥 =∑
2 (0 − 𝐸) d.f. = (rows – 1)(columns – 1)
𝐸

●●●
7
Non-parametric Test Methods

d.f. = (rows – 1) (columns – 1) = (2-1) (3-1) = (1) (2) = 2

●●●
7
Non-parametric Test Methods

Decision and Conclusion: Since the chi-square

value of 2.03 is less than the critical value of
5.991, then the null hypothesis is not rejected.
Meaning, there is not enough evidence to support
the claim that the spiciness level selected by an
individual is dependent of the gender of the
individual.

●●●
7
Advantages of Non-Parametric
Test
The advantages of the non-
parametric test are:
• Easily understandable
• Short calculations
• Assumption of distribution is not
required
• Applicable to all types of data

11
 Disadvantages of Non-
Parametric Test
The disadvantages of the non-
parametric test are:
• Less efficient as compared to
parametric test
• The results may or may not
provide an accurate answer
because they are distribution
free.

12
Applications of Non-Parametric
Test
The conditions when non-
parametric tests are used are
listed below:
• When parametric tests are not
satisfied.
• When testing the hypothesis, it
does not have any distribution.
• For quick data analysis.
• When unscaled data is available
13
 Conclusion

• The non-parametric test is one of the

methods of statistical analysis, which
does not require any distribution to
meet the required assumptions, that
has to be analyzed.
• Hence, the non-parametric test is called
a distribution-free test.

15