Free Tools › Kruskal-Wallis Test Calculator

Kruskal-Wallis Test Calculator

Compare three or more independent groups without assuming normality. Get the tie-corrected H statistic, p-value and epsilon squared.

FreeNo account neededYour data stays in your browser

Group 16 valuesGroup 27 valuesGroup 36 values

Results

H statistic (tie-corrected)	12.624
Degrees of freedom	2
p-value	0.002
Epsilon squared (ε²)	0.701Effect size
Group medians	5.50 · 4.00 · 12.00

A significant result means at least one group differs; use Dunn's post-hoc test to find which.

How to Use the Kruskal-Wallis Test Calculator

1
Enter each group
Paste values for two to six groups.
2
Read the result
H, df, p-value and effect size.

What is the Kruskal-Wallis test?

The Kruskal-Wallis H test is the rank-based alternative to one-way ANOVA. It tests whether several independent groups come from the same distribution, and suits skewed or ordinal data.

A significant result means at least one group differs; pairwise follow-up tests such as Dunn's test show which.

How it is calculated

H = 12/(N(N+1)) Σ Rᵢ²/nᵢ − 3(N+1), with average ranks for ties
Tie correction: H / (1 − Σ(t³ − t)/(N³ − N))
p-value from the chi-square distribution with k − 1 df
ε² = H / (N − 1)

Sources