Scribd
Upload
12 views6 pages

Nonparametric Tests

Nonparametric tests can be used when the assumptions of parametric tests are not met, including the chi-squared test, Mann-Whitney U test, Wilcoxon test, and Kruskal-Wallis test. The Mann-Whitney U test compares two independent samples, the Wilcoxon test compares two dependent samples, and the Kruskal-Wallis test compares several independent samples. Excel does not provide tools for these nonparametric tests, except for the chi-squared test.

Uploaded by

Thy Nguyễn
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
12 views6 pages

Nonparametric Tests

Nonparametric tests can be used when the assumptions of parametric tests are not met, including the chi-squared test, Mann-Whitney U test, Wilcoxon test, and Kruskal-Wallis test. The Mann-Whitney U test compares two independent samples, the Wilcoxon test compares two dependent samples, and the Kruskal-Wallis test compares several independent samples. Excel does not provide tools for these nonparametric tests, except for the chi-squared test.

Uploaded by

Thy Nguyễn
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Nonparametric tests

Toni Ernvall
Nonparametric tests
• Even if the requirements of the parametric tests presented above are
not met, it may still be possible to use so-called nonparametric tests.
• For example, the chi-squared test discussed before is a nonparametric
test.
• In addition to this, the following nonparametric tests are briefly
reviewed:
• Mann-Whitney U test
• Wilcoxon test
• Kruskal-Wallis test
Mann-Whitney U test
• The Mann-Whitney U test is a nonparametric equivalent of the
unpaired two-samples t-test.
• Hence, it can be used to compare two independent samples, even if
the assumptions related to the t-test (e.g. normality assumption) are
not valid.
Mann-Whitney U test

Sample 1 Sample 2
Wilcoxon test
• The Wilcoxon test is a nonparametric equivalent of the paired
samples t-test.
• Hence, it can be used to compare two dependent samples, even if the
assumptions related to the t-test (e.g. normality assumption) are not
valid.
Before After
Wilcoxon test

Sample 1 Sample 2
Kruskal-Wallis test
• The Kruskal-Wallis test is a nonparametric alternative for analysis of
variance.
• Hence, it can be used to compare several independent samples, even
if the assumptions related to the analysis of variance (e.g. the
normality assumption) are not valid.
Kruskal-Wallis test

Sample 1 Sample 2

Sample 3
Excel and nonparametric tests
As far as I know, there are no tools in Excel for implementing the
nonparametric tests mentioned in this course, except for the chi-
squared test.

You might also like