Saltar al contenido principal

LeveneTest

StatisticalTest
DashAI.back.statistical_tests.helper_tests.LeveneTest

Robust test for homogeneity of variances across groups.

This test evaluates whether several independent samples share a common variance while being less sensitive to departures from normality than Bartlett's test. It is commonly used as a preliminary check before applying parametric analyses such as ANOVA or t-tests, especially when the data may be mildly non-normal.

References

Levene, H. (1960). Robust Tests for Equality of Variances. In Olkin, I. et al. (eds.), Contributions to Probability and Statistics: Essays in Honor of Harold Hotelling, Stanford University Press.

Methods

get_metadata(cls) -> dict

Defined on LeveneTest

Metadata for Levene's Test.

run(self, scores: dict[str, list[float]], alpha: float = 0.05, **kwargs) -> DashAI.back.statistical_tests.statistical_test_result.StatisticalTestResult

Defined on LeveneTest

Run Levene's test for equality of variances across groups.

Parameters

scores : dict[str, list[float]]
Mapping from group names to score vectors whose variances will be compared.
alpha : float, optional
Significance level used to decide whether the variance equality assumption is rejected, by default 0.05.

Returns

StatisticalTestResult
A result object containing the Levene statistic, p-value, and the significance outcome.