331+ free tools. No sign-up. No hidden fees. Explore the toolkit

ANOVA Calculator

One-way ANOVA tests whether the means of three or more groups genuinely differ — or whether the differences you see could just be random variation. Paste up to 6 groups of data and get the F-statistic, the p-value, the sums of squares and the group means.

Choose how many groups you have, paste each group’s values, and get the F-statistic, p-value, sums of squares and the verdict at α = 0.05 instantly.

Separate values with commas, spaces or new lines. At least 1 value per group; total values must exceed the number of groups.

Result

Save to Pinterest
Note: The p-value comes from the F distribution, computed with the regularized incomplete beta function, accurate to about 1e-12 — the same method used by R and SciPy, cross-checked against SciPy 1.11.4. ANOVA assumes independent observations, roughly normal data within each group, and similar variances across groups. This calculator is for education and quick checks — it is not a substitute for professional statistical advice.

How It Works

One-way ANOVA asks whether several groups really have different means, or whether the differences you see could just be random variation. It does this by splitting the total variation in your data into two parts: SSB (sum of squares between groups), which measures how far each group mean sits from the grand mean, and SSW (sum of squares within groups), which measures how far each value sits from its own group mean. The two add up to the total: SST = SSB + SSW. Each sum of squares is divided by its degrees of freedom — k − 1 between groups (k = number of groups) and N − k within groups (N = total values) — giving the mean squares MSB and MSW. The test statistic is their ratio: F = MSB ÷ MSW. ANOVA needs enough values in each group to be meaningful — the sample size calculator works out how many you need.

If all the group means were truly equal, F would hover around 1. A large F means the groups differ more than random variation alone would explain. The p-value is the probability of an F at least this large under the F distribution, computed here with the regularized incomplete beta function — accurate to about 1e-12, the same method used by R and SciPy. If p is below your significance level (usually 0.05), the result is significant: at least one group mean differs.

Worked Example

Three groups of six values: A (6, 8, 4, 5, 3, 4) has mean 5.0000; B (8, 12, 9, 11, 6, 8) has mean 9.0000; C (13, 9, 11, 8, 7, 12) has mean 10.0000. The grand mean is 8.0000. SSB = 84.0000, SSW = 68.0000, SST = 152.0000, with 2 degrees of freedom between groups and 15 within. MSB = 42.0000, MSW = 4.5333, so F = 9.2647 and p = 0.0024 — significant at α = 0.05. If all three groups were identical, say [5, 6, 7] each, the group means would all be 6, SSB would be 0, F = 0.0000 and p = 1.0000 — no evidence of any difference at all.

Assumptions

Last reviewed: 15 November 2026.

Built and tested by SumKitTool — see how we check our numbers.

How to Use This Calculator

Choose how many groups you have, paste each group’s values, and the result updates live as you type.

  1. Choose the number of groups — from 2 to 6. Extra group boxes appear as you add groups.
  2. Enter each group’s data — paste values separated by commas, spaces or new lines. Each group needs at least 1 value, and the total must exceed the number of groups.
  3. Read the answer — the F-statistic, the p-value, the sums of squares and mean squares, the degrees of freedom, the group means and grand mean, and the verdict at α = 0.05.

The Reset button restores the worked example (three groups of six values — F = 9.2647, p = 0.0024).

Tips and Practical Advice

Frequently Asked Questions

What is one-way ANOVA used for?

One-way ANOVA (analysis of variance) tests whether the means of three or more independent groups differ from each other. For example, it can compare exam scores across three teaching methods, or crop yields across four fertilisers. With only two groups it gives the same p-value as a two-sample t-test — ANOVA earns its keep from three groups up, where running many separate t-tests would inflate the chance of a false positive.

How do I read the F-statistic and the p-value?

The F-statistic is the ratio of the variance between the groups to the variance within them: F = MSB ÷ MSW. A large F means the groups differ more than you would expect from random variation alone. The p-value is the chance of seeing an F at least this large if all the group means were really equal. For example, F = 9.2647 with 2 and 15 degrees of freedom gives p = 0.0024 — below 0.05, so the result is significant and at least one group mean differs. If p is above 0.05, the data does not show a real difference.

What are SSB, SSW and SST?

They split the total variation in your data into two parts. SSB (sum of squares between groups) measures how far each group mean sits from the grand mean, weighted by group size. SSW (sum of squares within groups) measures how far each value sits from its own group mean. SST (total sum of squares) is their sum: SST = SSB + SSW. In the worked example, SSB = 84.00 and SSW = 68.00, so SST = 152.00. Dividing each by its degrees of freedom gives the mean squares MSB and MSW, and their ratio is the F-statistic.

My ANOVA is significant — which groups actually differ?

ANOVA only tells you that at least one group mean differs; it does not say which ones. To find out, run a post-hoc test such as Tukey's HSD, which compares every pair of groups while keeping the overall false-positive rate at 0.05. Do not run plain t-tests on every pair after a significant ANOVA — with 4 groups that is 6 tests, and the chance of at least one false positive climbs to about 26%. Also check the assumptions: roughly normal data within each group, independent observations, and similar variances across groups.

Last updated: