Group 5

Glendell Atesora
Estelle Nica Marie Dunlao
Johny Sevilla
Jeoffrey Casipong
Elny Rose Vio
Zweetsel Señeres
Kruskal-Wallis
(H test)
2
The Kruskal-Wallis H test (sometimes also called
the "one-way ANOVA on ranks") is a rank-based
nonparametric test that can be used to
determine if there are statistically significant
differences between two or more groups of an
independent variable on a continuous or ordinal
dependent variable
https://statistics.laerd.com/spss-tutorials/kruskal-wallis-h-test-using-spss-statistics.php

3
The test determines whether the medians of two or more
groups are different. Like most statistical tests, you calculate a 
test statistic and compare it to a distribution cut-off point. The
test statistic used in this test is called the H statistic. The
hypotheses for the test are:

 H0: population medians are equal.

 H1: population medians are not equal.
 CONCEPTS
of Kruskal-Wallis (H test)
5
 Statistical Methods II

Non Parametric Testing –

The Kruskal-Wallis Test

Group 5

Second Reporter: Estelle Nica Marie Dunlao

 Kruskal-Wallis Test

 Hypotheses are written as:

H0: The k level means are the same
H1: At least one of means is
different
 Kruskal-Wallis Test
◉ is a rank-based nonparametric test that can be used to
determine if there are statistically significant differences
between two or more groups of an independent variable
on a continuous or ordinal dependent variable.
WHY?
- To test homogeneity of samples
- To test the equality of population medians
among groups
 S
Kruskal-Wallis Test Y
N
ll– H- Test
O
N
Rank one way Y
M
annova test S

Rank Sum Test

IS- Independent Samples
Kruskal-Wallis Test
ll– H- Test
The H test is used when the assumptions for ANOVA
aren’t met (like the assumption of normality

Rank one way ANOVA test The ranks of the data values are
used in the test rather than the
actual data points.

Rank Sum Test

We use the sum of the ranks of the k
samples to compare distributions

IS- Independent Samples

One way annova- the variation with in the group is equal

KW- does not assume that the data are normal

Kruskal-Wallis Test

ll– H- Test The H test is used when the assumptions for ANOVA aren’t met
(like the assumption of normality

Rank one way ANOVA

as the ranks of the data values are
used in the test rather than the actual
data points.

test
Example: Satisfaction Ratings in Assistance During Covid-19 Lockdown
LOW MIDDLE UPPER
7 4 10
6 1 5
8 3 2
7 7 3
5 9 4
Kruskal-Wallis Test the ranks of the data values are
used in the test rather than the actual
Rank one way annova test data points.

We use the sum of the ranks of the k

Rank Sum Test samples to compare distributions

Example: Satisfaction Ratings in Assitance During Covid-19 Lockdown

LOW MIDDL UPPER 1-1 6-9

E 2-2 7-10
3-3 7-11
7 4 10 3-4 7-12
11
4-5 8-13
6 1 5 4-6 9-14
3.5
5-7 10-15
8 3 2 5-8
7 7 3 5.5

5 9 4
R.LOW= 51.5 R. MID=35 R.HIGH= 33.5 7.5
 Kruskal-Wallis Test
 Like all non-parametric tests, the focus is on ranks, counting and the
medians.
 The hypotheses statements are written as:
H0: All k populations have the same median.
H1: Not all of the k population medians are the same.

 As the ANOVA is a conceptual extension of the two sample ttest, so

the K-W test is a conceptual extension of the Wilcoxon Rank Sum
(Mann Whitney) test.
Kruskal-Wallis (H test)
Examples
16
 KRUSKAL WALLES TEST
◉ - is a non-parametric alternative to the
oneway ANOVA.
◉ - means  that the test doesn’t assume your
data comes from a particular distribution.
The H test is used when the assumptions
for ANOVA aren’t met (like the 
assumption of normality). It is sometimes
called the one-way ANOVA on ranks, as
the ranks of the data values are used in
the test rather than the actual data points.
The test determines whether the medians of two or more
groups are different.
The test statistic used in this test is called the H
statistic. The hypotheses for the test are:
• H0: population medians are equal.
• H1: population medians are not equal.
 The Kruskal Wallis test will tell you if there is a significant difference
 between groups. However, it won’t tell you which groups are
different.
Therefore, running a post Hoc test is important.
◉ EXAMPLES:
◉ 1. You want to find out how test anxiety affects actual test scores. The
independent variable “test anxiety” has three levels: no anxiety, low-medium
anxiety and high anxiety. The dependent variable is the exam score, rated from 0 to
100%.
◉ 2. You want to find out how socioeconomic status affects attitude towards sales tax
increases. Your independent variable is “socioeconomic status” with three levels:
working class, middle class and wealthy. The dependent variable is measured on a
5-point Likert scale from strongly agree to strongly disagree.
 ASSUMPTIONS
for Kruskal-Wallis (H test)
20
21
22
26
 TEST STATISTIC FOR
THE KRUSKAL WALLIS
TEST
Running the H Test by hand
27
We have a statistically significant evidence at α =0.05, to show that there is a difference in the median of
salaries among the three different groups of workers.
 JASP
for Kruskal-Wallis (H test)
44
THANK YOU!


45