A paired-samples t-test (also called a dependent or repeated-measures t-test) compares two measurements taken from the same participants, for example a score before and after an intervention. Running it is easy. Writing it up so it passes review is where people lose marks. This guide gives you the exact APA 7 format, a worked example you can copy, and the errors reviewers flag most.
What you need before you write a single word
An APA 7 write-up of a paired t-test needs these values from your output:
- The mean (M) and standard deviation (SD) for each condition (for example, pre and post).
- The t value.
- The degrees of freedom (df). For a paired test this is the number of pairs minus 1.
- The exact p value.
- An effect size, usually Cohen's d for repeated measures. APA 7 expects an effect size, not just significance.
A 95% confidence interval for the mean difference is strongly encouraged in APA 7, so include it if your software reports it.
The APA 7 format template
Report the result in running text using this pattern:
A paired-samples t-test showed that [dependent variable] was significantly higher/lower at [condition 2] (M = X.XX, SD = X.XX) than at [condition 1] (M = X.XX, SD = X.XX), t(df) = X.XX, p = .XXX, d = X.XX, 95% CI [X.XX, X.XX].
Formatting rules reviewers actually check:
- Italicize the statistical symbols: M, SD, t, p, d, N.
- Put the degrees of freedom in parentheses right after t.
- No leading zero on p (it cannot exceed 1), so write p = .003, not 0.003.
- Keep the leading zero on Cohen's d (it can exceed 1), so write d = 0.68.
- Round most values to two decimals. Report p to two or three decimals, and if it is below .001, write p < .001 rather than p = .000.
A worked example
Suppose you measured anxiety scores before and after an eight-week mindfulness course in the same 25 participants.
- Before (n = 25): M = 48.20, SD = 9.10
- After (n = 25): M = 41.60, SD = 8.70
- Test result: t(24) = 3.42, p = .002, d = 0.68, 95% CI [2.62, 10.58]
Written up in APA 7, that becomes:
A paired-samples t-test showed that anxiety scores were significantly lower after the mindfulness course (M = 41.60, SD = 8.70) than before it (M = 48.20, SD = 9.10), t(24) = 3.42, p = .002, d = 0.68, 95% CI [2.62, 10.58].
That one sentence carries the direction of the change, the descriptive statistics for both conditions, the test result, the effect size, and the confidence interval.
The APA 7 table (optional but tidy)
For a results chapter, a small table keeps the descriptives out of the prose. APA tables use horizontal rules only, no vertical lines:
| Condition | n | M | SD |
|---|---|---|---|
| Before | 25 | 48.20 | 9.10 |
| After | 25 | 41.60 | 8.70 |
Note. Anxiety measured on a 0 to 60 scale. The reduction was significant, t(24) = 3.42, p = .002, d = 0.68.
Mistakes reviewers catch
- Reporting it as an independent t-test. A paired design compares the same people twice; the df is pairs minus 1, not n1 + n2 minus 2. Using the wrong test is a substantive error, not a formatting one.
- Writing p = .000. No p value is exactly zero. Report p < .001.
- A leading zero on p. APA drops it for anything that cannot exceed 1.
- No effect size. "Significant" alone does not tell the reader how large the change was. Report Cohen's d.
- Missing the direction. State which condition was higher, not just that they differed.
- Confusing the CI. In a paired test the 95% CI is for the mean of the differences, not for either condition's mean.
Before you report: did the test's assumptions hold?
A paired t-test is defensible only if its assumptions hold. It assumes:
- Paired, related observations (each score in one condition matches a score in the other from the same unit).
- Approximate normality of the difference scores, not of the raw scores in each condition.
If the difference scores are badly non-normal, the Wilcoxon signed-rank test is the usual non-parametric alternative, and it has its own APA format.
Let KyroStat do the write-up for you
Formatting statistics by hand is where errors creep in. KyroStat runs the paired-samples t-test on your data, checks the normality of the difference scores, and hands you the finished APA 7 sentence, a publication-ready table, the plot, and the underlying Python or R code so you and your reviewers can see exactly how every number was produced. Upload your spreadsheet, and the report is done in seconds.
Frequently asked questions
What is the difference between a paired and an independent t-test? A paired test compares two measurements from the same participants (before and after, or two conditions each person completed). An independent test compares two separate groups of different people.
What degrees of freedom does a paired t-test use? The number of pairs minus 1. With 25 participants measured twice, df = 24.
Which effect size should I report? Cohen's d for repeated measures. Report it with a leading zero, for example d = 0.68.
My p value shows as .000. What do I write? Report p < .001. A p value is never exactly zero.