← Back to Statistics
Non-Parametric Tests
Kruskal-Wallis Test
Rank-based comparison across three or more independent groups.
Calculation engine
Client-side JavaScript; no external statistics package is loaded.
Results are calculated in the browser and are not uploaded.
Client-side JavaScript; no external statistics package is loaded.
Results are calculated in the browser and are not uploaded.
Method overview
When to use
Use as a non-parametric alternative to one-way ANOVA for independent groups.
Input requirements
Enter one group per line. At least 3 groups are required and each group needs at least 2 values.
Key assumptions
- Independent observations.
- Outcome is at least ordinal.
- Groups should have similarly shaped distributions for simple location interpretation.
Null hypothesis
H₀: all groups have the same rank distribution.
Method used
Kruskal-Wallis H statistic with chi-square approximation.
References
- Kruskal WH, Wallis WA. Use of ranks in one-criterion variance analysis. JASA, 1952.
Data input and results
Enter one group box per independent group. This is the rank-based alternative to one-way ANOVA.
No calculation has been performed.