Levene's Test Calculator: Equal Variances with Brown–Forsythe, Bartlett and Fligner–Killeen
ANOVA and the classic t-test assume the groups have similar variances. Paste one column per group (or a group column and a value column) to test that assumption with Levene’s test, the Brown–Forsythe version, Bartlett’s test, the Fligner–Killeen test and, for two groups, the F-test. You get a recommendation, a spread chart and an APA sentence. Results match R’s car::leveneTest(), bartlett.test(), fligner.test() and var.test().
- PriceFree, no login or sign-up needed
- Your dataProcessed in your browser, never uploaded
- Works onPhone, tablet or computer, any modern browser
- Made byDr. Muhammad Aammar Tufail, Codanics
- Published17 November 2026
- Last updated16 November 2026
📚 How to cite this tool
This tool is free. If it helped your thesis, paper, report or assignment, please cite it. It keeps the tools free and helps other students find them.
Tufail, M. A. (2026). Levene's test calculator [Online tool]. Codanics. Retrieved 16 November 2026, from https://codanics.com/tools/levene-test-calculator/
In-text citation: (Tufail, 2026) · Narrative: Tufail (2026)
The access date is today’s date, filled in automatically. Author: Muhammad Aammar Tufail. Published 17 November 2026.
How to use the levene's test calculator
- Type or paste each group’s values into its own box, or use Paste from Excel / Upload CSV / Excel with one column per group or a group column plus a value column. Add more groups with + Add group.
- Choose α and the test you want to report. Brown–Forsythe (median-centred Levene) is the robust default; choose Levene (mean) to match SPSS.
- Click Test equal variances. Read the conclusion, the variance ratio and the recommendation for which ANOVA or t-test to use.
- Copy the sentence and tables for Word, download the CSV, or save the spread chart as PNG or SVG.
Which equal-variance test should I use?
| Test | Centre | Sensitive to non-normality? | Use when |
|---|---|---|---|
| Brown–Forsythe | Median | Low | The robust default; what car::leveneTest() gives in R. |
| Levene | Mean | Moderate | To match SPSS (“Based on Mean”) or when data are clearly normal. |
| Bartlett | – | High | Only when data are normal; most powerful then, but skewness alone can make it significant. |
| Fligner–Killeen | Median, ranks | Very low | Skewed data or outliers. |
| F-test | – | High | Exactly two groups with normal data. Gives a CI for the variance ratio. |
How the tests work
Worked example
The example is R’s PlantGrowth data (dried plant weight under a control and two treatments, 10 plants each). SDs are 0.58, 0.79 and 0.44. Brown–Forsythe gives F(2, 27) = 1.119, p = .341; Levene (mean) F(2, 27) = 1.237, p = .306; Bartlett K² = 2.879, p = .237; Fligner–Killeen χ² = 2.350, p = .309. None is significant, so a classic one-way ANOVA is reasonable. These numbers are identical to R.
How to report it
“Levene’s test (median-centred) indicated that the assumption of homogeneity of variance was met, F(2, 27) = 1.12, p = .341.” If it is violated: “Because variances differed (Brown–Forsythe F(3, 36) = 4.21, p = .012), Welch’s ANOVA with Games–Howell post-hoc tests was used.”
Frequently asked questions
What is the difference between Levene's test and the Brown–Forsythe test?
Both run an ANOVA on the absolute deviations from each group’s centre. Levene’s original test uses the mean; Brown–Forsythe uses the median, which makes it more robust to skewed data. R’s car::leveneTest uses the median by default; SPSS reports both.
What does a significant Levene's test mean?
A p-value below α means the group variances differ, so the equal-variance assumption of the classic ANOVA or Student’s t-test is violated. Use Welch’s ANOVA with Games–Howell, or Welch’s t-test, instead.
Why does SPSS give a different Levene value?
SPSS’s main row is ‘Based on Mean’ (Levene’s original test). Choose ‘Levene (mean-centred)’ here to match it. ‘Based on Median’ in SPSS equals Brown–Forsythe.
Should I use Bartlett's test?
Only if you are confident the data are normal. Bartlett’s test is very sensitive to non-normality, so a significant result may reflect skewness rather than unequal variances.
What variance ratio is acceptable?
A common rule of thumb is that ANOVA is fairly robust if the largest variance is less than about 4 times the smallest (SD ratio below 2), especially with equal group sizes.
Is my data uploaded?
No. All calculations run in your browser and nothing is stored or sent anywhere.
Do I need to log in or create an account to use the levene's test calculator?
No. There is no login, no sign-up and no email required. Open the page and start using it straight away, for free, on any device.
How do I cite this tool in my thesis or paper?
Use the citation box on this page. In APA 7th edition: Tufail, M. A. (2026). Levene's test calculator [Online tool]. Codanics. Retrieved [date you used it], from https://codanics.com/tools/levene-test-calculator/. BibTeX, RIS (EndNote, Mendeley, Zotero), MLA, Harvard, Chicago and Vancouver formats are also available.
Free guides and courses from Codanics
More free tools
See all free Codanics tools → · Codanics on YouTube · WhatsApp channel