Kruskal-Wallis Test for Three or More Independent Samples
The Kruskal-Wallis test uses sample data from three or more independent samples to test the null hypothesis that the samples are from populations with the same median.
Let's consider Example 1 in Section 13-5. Begin by entering the sample data (Table 13-6 in the textbook) in three columns as shown in the StatCrunch Data window at the end of this report.
In StatCrunch, click on Stat, click on Nonparametrics, then select Kruskal-Wallis.
In the next window, select the columns containing the sample data, as shown below.
|
|
Click onCalculate to get these results:
|
Kruskal-Wallis results:
Data stored in separate columns. Chi Square = 5.8345547 (adjusted for ties) DF = 2 P-value = 0.0541
|
Interpreting Results: See that the above results include the P-value of 0.0541. Because that P-value is large (greater than 0.05), we fail to reject the null hypothesis of equal population medians, and we get the same conclusions given in Example 1 in the textbook.
