Levene's Test

Levene's Test

Overview

Definition

Levene's Test assesses the assumption of Homogeneity of Variance (Equal Variances) required by T-Tests and ANOVA.

$H_{0}$ : Variances are equal.
$H_{1}$ : Variances are not equal.

Interpretation

Significant (p < 0.05): Bad news. Variances are unequal. Switch to Welch's T-Test.
Not Significant (p > 0.05): Good news. Assumption met.

1. Python Implementation

from scipy import stats
# Compare variances of Group A and Group B
stat, p = stats.levene(group_A, group_B)

if p < 0.05:
    print("Variances Unequal (Use Welch)")

2. R Implementation

library(car)

# leveneTest(Outcome ~ Group)
leveneTest(Score ~ Group, data = df)

# Note: The car package version is robust (uses deviations from median).