Paired Samples t-Test Calculator
The paired t-test compares two measurements taken on the same subjects — before/after an intervention, two conditions, or matched pairs. Paste both measurement columns (or enter the number of pairs with the mean and SD of the differences) and instantly get the t statistic, p-value, mean difference with 95% confidence interval and the effect size Cohen's dz. The test's key assumption — that the differences are normally distributed — is checked automatically with Shapiro-Wilk, and a plain-language interpretation tells you what the numbers mean. Results match R's t.test(paired = TRUE) to at least six significant digits; the AI Report turns them into an APA 7 paragraph.
AI Report
Let AI interpret your results: a downloadable Word document in APA 7 / business report format.
Frequently asked questions
How do I report paired t-test results in APA 7 format?
Include the mean difference, t with df, p-value and effect size, e.g.: "Scores improved significantly from pretest to posttest, t(9) = 3.25, p = .010, dz = 1.03, 95% CI of the difference [0.21, 1.09]." The AI Report button writes the full APA results paragraph for you.
When should I use a paired t-test instead of an independent t-test?
Use the paired test whenever the two sets of values come from the same subjects (repeated measures) or from naturally matched pairs. Pairing removes between-subject variability and gives you more statistical power than treating the groups as independent.
What is Cohen's dz?
It is the effect size for paired designs: the mean of the differences divided by the standard deviation of the differences. It is what G*Power calls 'dz' in its paired t-test module, so you can plug it directly into a power analysis.
What if the differences are not normally distributed?
With clear violations and small samples, the Wilcoxon signed-rank test is the usual non-parametric alternative. The automatic Shapiro-Wilk check below the result warns you when this is worth considering.