Example Data Table
| Subject |
Before |
After |
After minus before |
| 1 | 72 | 78 | 6 |
| 2 | 65 | 70 | 5 |
| 3 | 81 | 86 | 5 |
| 4 | 90 | 92 | 2 |
| 5 | 74 | 79 | 5 |
Formula Used
Difference score: d = after score − before score
Mean difference: d̄ = sum of differences / n
Standard deviation of differences: sd = square root of sum(d − d̄)² / (n − 1)
Standard error: SE = sd / square root of n
Test statistic: t = (d̄ − hypothesized difference) / SE
Degrees of freedom: df = n − 1
Confidence interval: d̄ ± t critical × SE
Cohen dz: d̄ / sd
How to Use This Calculator
Enter paired scores in the large data box. Place the first score before the comma. Place the second score after the comma.
Set the hypothesized mean difference. Most repeated measures tests use zero. Select alpha, confidence level, test direction, and difference direction.
Press the calculate button. The result appears above the form and below the header. Review the p value, confidence interval, effect size, and decision.
Use the CSV button for spreadsheet work. Use the PDF button for a clean report copy.
Repeated Measures T Test Guide
A repeated measures t test compares two scores from the same subjects. It is also called a paired samples t test. The method focuses on each subject’s change, not on two unrelated groups. This calculator is useful for before and after studies, matched designs, training checks, medical follow ups, classroom tests, product trials, and repeated lab readings.
Why paired data matters
Paired data removes much person to person variation. Each row becomes one difference score. The test then asks whether the average difference is far enough from the hypothesized mean difference. Most studies use zero as that reference value. A positive mean difference means the second measure is higher. A negative value means the second measure is lower.
What the result shows
The output gives the mean before score, mean after score, average difference, standard deviation of differences, standard error, degrees of freedom, t statistic, p value, confidence interval, and effect size. Cohen’s dz uses the mean difference divided by the standard deviation of differences. The calculator also reports a paired correlation, which helps show how strongly both measurements move together.
Choosing a tail option
Use a two tailed test when any change matters. Use a right tailed test when you expect the after score to be greater. Use a left tailed test when you expect the after score to be smaller. Choose the tail before seeing the result. That keeps the analysis honest.
Checking assumptions
The main assumption is that difference scores are reasonably continuous and roughly normal. With larger samples, the test is usually more stable. Extreme outliers can change the result. Review the row table before accepting the conclusion. If differences are strongly skewed, consider a nonparametric paired test as a sensitivity check.
Reporting the finding
A clear report includes n, df, t, p, the mean difference, and the confidence interval. Also include the measurement direction. For example, after minus before should be stated. This prevents confusing improvements with declines. Keep units consistent across both columns. Remove empty rows before running final analysis. Label each dataset version clearly during review. Export the CSV for spreadsheets. Use the PDF option when a simple record is needed for notes, audit files, or client reports.
FAQs
What is a repeated measures t test?
It compares two related measurements from the same subjects. It tests whether the average difference is statistically different from a chosen value, usually zero.
Is this the same as a paired t test?
Yes. A repeated measures t test is commonly called a paired samples t test. Both names refer to testing matched or repeated observations.
What data format should I enter?
Enter one pair per line. Use before,after format. If your rows include subject IDs, check the ID column option before calculating.
Which tail option should I choose?
Choose two tailed when any change matters. Choose right tailed for expected increases. Choose left tailed for expected decreases.
What does Cohen dz mean?
Cohen dz is an effect size for paired data. It divides the mean difference by the standard deviation of the difference scores.
What does the confidence interval show?
It shows a likely range for the true mean difference. If the interval excludes zero, the paired change may be statistically meaningful.
Can I use unequal sample sizes?
No. Each before score must have one matching after score. Repeated measures designs require paired observations for every included row.
When should I avoid this test?
Avoid it when pairs are not related, differences have severe outliers, or the outcome is not reasonably continuous. Consider another method then.