📐 T-Test Calculator
Enter your sample means, standard deviations and sizes to run a t-test — with the t statistic, df, exact p-value and whether the result is significant.
Sample 1
Sample 2
t statistic
-3.038
Degrees of freedom
50.53
p-value
0.0038
Statistically significant at α = 0.05
p = 0.0038 < 0.05, so you reject the null hypothesis — the observed difference is unlikely to be due to chance alone.
Uses Student's t-test with exact t-distribution p-values. The two-sample test defaults to Welch's (unequal-variance) form, which is safer when the group sizes or spreads differ; tick "equal variances" for the classic pooled test. Enter summary statistics (mean, SD, n) — for a paired test, use the mean and SD of the paired differences. "Fail to reject" is not proof of no effect, only insufficient evidence. 🔒 In your browser.
How the t-test calculator works
A t-test asks whether a difference in means is real or just chance. The tool computes the t statistic — the difference in means divided by its standard error — and converts it to an exact p-value using the Student t-distribution. It handles a one-sample test (mean vs a hypothesized value), a two-sample test (defaulting to Welch's unequal-variance form, with a pooled option), and a paired test (on the mean and SD of the differences), for one- or two-tailed hypotheses.
Enter summary statistics rather than raw data. The two-sample test defaults to Welch's test, which is more reliable than the classic pooled test when the groups have different sizes or spreads. A p-value below your significance level (α, usually 0.05) means you reject the null hypothesis; "failing to reject" is not proof there's no effect, only that the evidence is insufficient. The t-test assumes roughly normal data.
Frequently asked questions
How do I calculate a t-test?
Compute t = (difference in means) ÷ (standard error of that difference), find the degrees of freedom, and convert t to a p-value using the t-distribution. Enter your means, standard deviations and sample sizes and the tool does all three exactly.
What is the difference between a one-sample, two-sample and paired t-test?
A one-sample test compares one group's mean to a fixed value; a two-sample test compares the means of two independent groups; a paired test compares two measurements on the same subjects (before/after) by testing whether their differences average to zero.
What is the difference between Welch and pooled t-tests?
The pooled (Student) test assumes the two groups have equal variances; Welch's test does not, and is more robust when variances or sample sizes differ. Welch's is the safer default — use pooled only when equal variances are justified.
What does the p-value mean in a t-test?
The probability of seeing a difference at least this large if the null hypothesis (no real difference) were true. A small p-value (below α, typically 0.05) suggests the difference is unlikely to be chance, so you reject the null hypothesis.
When should I use one-tailed vs two-tailed?
Use two-tailed (the default) when you're testing for any difference in either direction. Use one-tailed only when you have a specific directional hypothesis decided in advance (e.g. the new method is faster), since it concentrates all the significance on one side.