Mean difference and t statistic
Compare independent or paired samples using mean difference, standard error, t statistic and degrees of freedom.
The example value has been entered. Check it immediately or change the value.
Input is processed in the browser. Refreshing returns a sample value.
Instructions and example
Independent: SE=√(sA²/nA+sB²/nB), Welch degrees of freedom. Paired: d=A−B, SE=sd/√n. t=mean difference/SE.
Independent A=1,2,3 and B=2,4,6 give difference −2, SE≈1.29099444874 and degrees of freedom≈2.94117647059.
Each sample has 2–1,000 values with absolute value at most 1,000,000,000. Sample variance uses n−1; no p-value or significance verdict is provided. Floating-point results display at most 12 significant digits.
Frequently asked questions
Does order matter for paired samples?
Yes. Matching positions must refer to the same subject. Unequal lengths are rejected; pairs are not inferred.
What happens when the standard error is 0?
The t statistic is undefined. Constant observations do not automatically produce a significance conclusion.
Calculation criteria and reference materials
- NIST: two-sample t-test
Independent-sample mean comparison and Welch degrees of freedom.
Verification of calculation criteria: · Calculation·verification principles · Report errors