← Back to Statistics
T-Tests

Paired Samples T-Test

Compare paired or before-after continuous measurements.

Calculation engine
Client-side JavaScript; no external statistics package is loaded.
Results are calculated in the browser and are not uploaded.

Method overview

When to use

Use when the same subjects are measured twice, or when observations are naturally matched.

Input requirements

Enter two numeric vectors with the same number of values. The first value in group 1 is paired with the first value in group 2.

Key assumptions

  • Pairs are correctly matched.
  • Differences between paired values are approximately normally distributed.
  • The paired differences are independent across subjects.

Null hypothesis

H₀: the mean paired difference equals 0.

Method used

One-sample t-test applied to paired differences; P value from the t distribution.

References

  • Altman DG. Practical Statistics for Medical Research. Chapman & Hall, 1991.

Data input and results

For paired data, raw mode requires two columns in the same order. Summary mode requires n, mean paired difference and SD of paired differences.

No calculation has been performed.