KruskalWallisTest<T>

Models & Types · AiDotNet.Evaluation.Statistics

Kruskal-Wallis H test for comparing multiple independent groups.

Implements: IMultipleComparisonTest<T>

For Beginners

Kruskal-Wallis is the non-parametric alternative to one-way ANOVA:

  • Compares medians of 3+ independent groups
  • No assumption of normal distribution
  • Uses ranks instead of raw values
  • Tests if at least one group differs from others

How It Works

Difference from Friedman test:

  • Kruskal-Wallis: independent groups (different samples)
  • Friedman: paired/matched groups (same samples, different treatments)

Constructors

Constructor Summary
KruskalWallisTest()

Properties

Property Summary
bool IsNonParametric { get; }
bool IsPaired { get; }
string Description { get; }
string Name { get; }

Methods

Method Summary
Dictionary<ValueTuple<int, int>, double> DunnPostHoc(T[][] groups) Performs Dunn’s post-hoc test for pairwise comparisons.
StatisticalTestResult<T> Test(T[][] groups) Tests if multiple groups have significantly different distributions.