Part of the Maths & Statistics suite · 235 calculators

T-Test Calculator

A one-sample or two-sample t-test with the exact p-value — whether a mean differs from a claimed value, or two groups differ from each other.

A t-test asks whether a difference in means is larger than sampling noise would comfortably produce.

Results update as you type
Results
t statistic
1.7219
Two-tailed p-value
Degrees of freedom
Sample mean
Second mean, or claimed mean
At the 5% level
Reviewed September 2026. Pure mathematics: the result does not depend on where you are. Terminology follows the Australian Curriculum (maths, brackets, decimal point).
No account required · Google Analytics off unless allowedCalculator arithmetic runs in your browserResults update as you type
All calculations run 100% in your browser. The calculator code does not submit your figures to GlobalCalc to obtain a result.
About t-test

How the t-test calculator works

A t-test asks whether a difference in means is larger than sampling noise would comfortably produce. The t statistic is the difference divided by its standard error, and the p-value is the probability of seeing a difference at least that large if there were really no difference at all.

The p-value here is exact, from the incomplete beta function, rather than a normal approximation — which matters most with small samples, exactly where t-tests are used. A p below 0.05 is the conventional threshold, but it is a convention, not a discovery: it says the data would be unusual under the null hypothesis, not that the effect is large or important.

Formula: one sample: t = (x̄ − μ) ÷ (s ÷ √n); two sample: t = (x̄₁ − x̄₂) ÷ SE

Worked examples

Inputst statisticNote
One sample against a claimed mean of 51.7219t = 1.83, p = 0.11 — not significant
Two groups that clearly differ-5.2754p well below 0.001
A sample centred exactly on the claim0t = 0, p = 1

Frequently asked questions

What does a t-test tell me?

Whether a difference in means is bigger than sampling noise would comfortably produce. It does not tell you the difference matters.

What does p < 0.05 mean?

That data this extreme would occur less than 5% of the time if there were really no difference. It is a convention, not a proof.

Is a p-value the probability the null is true?

No, and this is the commonest misreading. It is the probability of the data given the null, not of the null given the data.

One-sample or two-sample?

One sample compares a group against a claimed value; two samples compare two groups with each other.

Does this assume equal variances?

No — the two-sample test uses Welch's correction, which does not, and is the safer default.

Where these figures come from

Last checked: September 2026. Formulas are fixed by mathematics and do not change with tax years or regulations.