h2(#description). Description

In this template Rapporter will present you Kruskal Wallis test.

h3(#introduction). Introduction

"Kruskal-Wallis test":http://en.wikipedia.org/wiki/Kruskal-Wallis is a non-parametric statistical test that assesses hypothesis of equality of two independent sample's/variabels' variances. Most of the time it's being used beacuse the normality assumptions didn't meet for the samples/variables, but we need the assumption of the equal variances, so it can be an alternative of the Two-sample t-test. Significant result means difference between the samples/variables.

<table>
<caption>Kruskal-Wallis test for _Age_ and _Internet usage for educational purposes (hours per day)_</caption>
<col width="23%" />
<col width="6%" />
<col width="25%" />
<thead>
<tr class="header">
<th align="center">Test statistic</th>
<th align="center">df</th>
<th align="center">P value</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td align="center">1010</td>
<td align="center">1</td>
<td align="center">_1.056e-221_ &#42; &#42; &#42;</td>
</tr>
</tbody>
</table>

As you can see in the table the test's degrees of freedom is _1_, the joint test-statistic is _1010_, so the p-value of the Kruskal-Wallis test is _1.056e-221_. Thus we can reject the assumption of the equal variances.

h2(#description-1). Description

In this template Rapporter will present you Kruskal Wallis test.

h3(#introduction-1). Introduction

"Kruskal-Wallis test":http://en.wikipedia.org/wiki/Kruskal-Wallis is a non-parametric statistical test that assesses hypothesis of equality of two independent sample's/variabels' variances. Most of the time it's being used beacuse the normality assumptions didn't meet for the samples/variables, but we need the assumption of the equal variances, so it can be an alternative of the Two-sample t-test. Significant result means difference between the samples/variables.

<table>
<caption>Kruskal-Wallis test for _mpg_ and _drat_</caption>
<col width="23%" />
<col width="6%" />
<col width="22%" />
<thead>
<tr class="header">
<th align="center">Test statistic</th>
<th align="center">df</th>
<th align="center">P value</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td align="center">47.28</td>
<td align="center">1</td>
<td align="center">_6.14e-12_ &#42; &#42; &#42;</td>
</tr>
</tbody>
</table>

As you can see in the table the test's degrees of freedom is _1_, the joint test-statistic is _47.28_, so the p-value of the Kruskal-Wallis test is _6.14e-12_. Thus we can reject the assumption of the equal variances.

<hr />

This report was generated with "R":http://www.r-project.org/ (3.0.1) and "rapport":https://rapporter.github.io/rapport/ (0.51) in _0.267_ sec on x86&#95;64-unknown-linux-gnu platform.

!images/logo.png!