Table of contents
1. What is it ?
2. How to use it on EasyMedStat ?
The Kruskal-Wallis test is a replacement for the Mann-Whitney test when comparing more than 2 independent groups of patients
What is it ?
The Kruskal-Wallis H test (named after William Kruskal and W. Allen Wallis), or One-way ANOVA on ranks is a non-parametric method for testing distributions between independent groups of patients. The H0 hypothesis is that all groups have the same median value, or come from the same population
. When rejecting H0, we can say that at least one sample is different from the others
, but without saying which one is statistically different.
Since it is a non-parametric method, the Kruskal-Wallis test does not assume a normal distribution of the residuals, unlike the analogous one-way ANOVA
, and can then be used with small samples.
How to use it on EasyMedStat ?
On EasyMedStat, you can use the Kruskal-Wallis test with the function Test 2 Variables
- You select a Numeric variable you would like to compare between groups, let's say a functional score (Min = 0, Max = 100), and then you select a List variable to create groups of patients, for example "Dominant hand".
- You will get 3 groups of patients : "Right-handed", "Left-handed", "Ambidextrous", with a mean "Total Score" for each group.
- A BoxPlot will be displayed and then the Kruskal-Wallis test will be performed, telling you if at least one distribution is different from the others.
NB : If there are only 2 groups to compare (Yes-no variables), another test will be done according to pairing and sample size
Copyright EasyMedStat© 2013
Easy Made Stat - Association Loi 1901 - n° W922009408
Neuilly-sur-Seine - France
Contact us - Legal terms