DataCamp

Nonparametric methods: The Kruskall-Wallis test

Just as the comparison of means across two groups can be extended to a comparison of means across many groups, the non-parametric approach to compare mean ranks between two groups can also be extended to multiple groups. The test that does this is called the Kruskall-Wallis test which is a non-parametric counterpart of the one-way analysis of variance. In the exercises on using the Kruskall-Wallis test, we will be working with our example of beer. However, we will extend this example by introducing a third beer type that is being tested by our test panel: the amber ale.

Before we move on to doing a Kruskall-Wallis test in R, let's first get our hypotheses for this new experiment. Because we just introduced a new type of beer, we have no preliminary evidence for which beer may be best. Choose the most appropriate set of hypotheses using this example given the fact that we do not want to indicate directionality in our hypotheses.

Possible Answers

H0: There is no difference in satisfaction between the different beer groups. H1: There is a difference in satisfaction between the different beer groups.
press 1
H0: There is no difference in satisfaction between the different beer groups. H1: The IPA group experiences greater satisfaction than the other beer groups.
press 2
H0: There is no difference in satisfaction between the different beer groups. The amber ale experiences greater satisfaciton than the other beer groups.
press 3

Take Hint (-15 XP)

Exercise

Nonparametric methods: The Kruskall-Wallis test

Instructions

Possible Answers