Advanced Levene Test Calculator

Input samples, choosing mean or median centers. Check homogeneity assumptions before ANOVA with detailed diagnostics. Download outputs, reuse examples, and visualize dispersion trends easily.

Levene test calculator

Use one stacked page. The calculator area uses 3 columns on large screens, 2 on smaller screens, and 1 on mobile.

Separate values with commas, spaces, semicolons, or new lines.
Separate values with commas, spaces, semicolons, or new lines.
Separate values with commas, spaces, semicolons, or new lines.

Example data table

This example is also available through the “Load example data” button.

Group Values
Group A 12, 15, 14, 13, 16, 15
Group B 11, 10, 12, 13, 11, 12
Group C 18, 19, 17, 20, 18, 21

Formula used

Step 1: For each group, choose a center Ti. Use the mean, median, or trimmed mean.
Step 2: Transform each observation into an absolute deviation: Zij = |Xij - Ti|.
Step 3: Run a one-way ANOVA on the Z values:

W = ((N - k) / (k - 1)) × [ Σ ni(Z̄i - Z̄)2 / ΣΣ(Zij - Z̄i)2 ]

Where:

How to use this calculator

  1. Enter at least two groups and give each group two or more numeric observations.
  2. Choose a center method. Median is often preferred when normality is uncertain.
  3. Set alpha to match your reporting standard, such as 0.05 or 0.01.
  4. Click “Run Levene test” to see the statistic, p value, decision, table, and graph.
  5. Use the CSV button for spreadsheet review and the PDF button for reports or client delivery.
  6. Interpret the result before ANOVA. A small p value suggests unequal variances across groups.

Frequently asked questions

1) What does Levene’s test check?

It checks whether multiple groups have similar variances. Researchers often run it before ANOVA because unequal variances can affect model assumptions and interpretation quality.

2) When should I choose the median option?

Choose the median when your data may include outliers or departures from normality. This version is commonly called the Brown-Forsythe approach.

3) What does a small p value mean?

A small p value means the variance differences are unlikely under the equal-variance assumption. You may need robust methods, data transformation, or unequal-variance procedures.

4) Can I use different group sizes?

Yes. The groups do not need equal sample sizes. However, each group should contain enough observations to produce stable variance information.

5) Does this replace normality testing?

No. Levene’s test focuses on variance equality, not distribution shape. You may still examine histograms, Q-Q plots, or other normality checks separately.

6) Why are absolute deviations used?

Absolute deviations convert each raw observation into a distance from its group center. Then an ANOVA-style comparison measures whether those distances differ by group.

7) What is the trimmed mean option for?

The trimmed mean option removes a small percentage of extreme values from each tail before computing the center. It balances sensitivity and robustness.

8) Can I export the output?

Yes. The page provides CSV and PDF download buttons after a calculation. They export the summary and detailed group statistics for sharing or archiving.

Related Calculators

brunner munzel testspearman rank correlation calculatorkolmogorov smirnov test calculatoriqr calculatorkernel density estimatorfisher exact test calculatorgoodman kruskal gammacramer v calculatortheil sen estimatorkruskal wallis test calculator

Important Note: All the Calculators listed in this site are for educational purpose only and we do not guarentee the accuracy of results. Please do consult with other sources as well.