How to Report an Independent-Samples t-Test in APA 7
Academic Decoder (@academicdecoder)
Created by a PhD-qualified lecturer · Updated
The short answer
In APA 7, an independent-samples t-test is reported with each group's mean and standard deviation, then t(df), the exact p-value, an effect size (Cohen's d), and the 95% confidence interval of the mean difference. Use the template that matches your result.
An independent-samples t-test was conducted to compare outcome between Group 1 (M = mean, SD = SD) and Group 2 (M = mean, SD = SD). Results indicated a statistically significant difference, with higher-scoring group scoring significantly higher than other group, t(df) = t, p = p, d = Cohen's d. The mean difference (Group 1 − Group 2) was difference, 95% CI [lower limit, upper limit].
An independent-samples t-test was conducted to compare outcome between Group 1 (M = mean, SD = SD) and Group 2 (M = mean, SD = SD). The difference was not statistically significant, t(df) = t, p = p, d = Cohen's d. The mean difference (Group 1 − Group 2) was difference, 95% CI [lower limit, upper limit].
This guide is for undergraduate and master's students writing a dissertation results chapter. It covers which numbers to take from SPSS, jamovi or R, worked examples, the formatting rules, and how to word a non-significant result.
What to report, and where to find it
You need six values and one decision (which row of the output you used). Most values can be obtained directly from statistical software, although some may require additional options or calculations.
M and SD for each group
- What it tells the reader
- The direction and spread of scores
- SPSS
- Group Statistics table
- jamovi
- Descriptives (under Additional Statistics)
- R
psych::describeBy()
t
- What it tells the reader
- The mean difference relative to its standard error
- SPSS
- Independent Samples Test, column t
- jamovi
- Statistic
- R
t.test()output, t
df
- What it tells the reader
- Degrees of freedom (n₁ + n₂ − 2, or Welch's df)
- SPSS
- Column df
- jamovi
- df
- R
- df
p
- What it tells the reader
- Whether the difference is statistically significant
- SPSS
- Sig. (2-tailed), or Two-Sided p in newer versions
- jamovi
- p
- R
- p-value
Cohen's d
- What it tells the reader
- How large the difference is, in standard-deviation units
- SPSS
- Independent Samples Effect Sizes table (SPSS 27+)
- jamovi
- Effect size (tick Cohen's d)
- R
effectsize::cohens_d()
Mean difference and its 95% CI
- What it tells the reader
- The size of the raw difference and a range of plausible values for it in the population
- SPSS
- Mean Difference; 95% Confidence Interval of the Difference
- jamovi
- Mean difference; Confidence interval
- R
- Difference of the two means; 95 percent confidence interval
Which row you used
- What it tells the reader
- Whether equal variances were assumed
- SPSS
- Equal variances assumed / not assumed
- jamovi
- Student's / Welch's
- R
var.equal = TRUE(Student) or the default (Welch)
If Levene's test is significant, or your groups differ a lot in size, report the Welch (equal variances not assumed) row. Many methodologists now recommend Welch's test by default, so check what your supervisor or department expects.
Worked example
A researcher compares wellbeing scores between an intervention group and a control group, with 30 participants in each. These are sample data for illustration.
| Group | M | SD | n |
|---|---|---|---|
| Intervention | 24.60 | 5.20 | 30 |
| Control | 20.90 | 5.80 | 30 |
Test result (Student's t-test): t(58) = 2.60, p = .012, Cohen's d = 0.67. Mean difference (Intervention − Control) = 3.70, 95% CI of the mean difference [0.85, 6.55].
An independent-samples t-test was conducted to compare wellbeing score between Intervention (M = 24.60, SD = 5.20) and Control (M = 20.90, SD = 5.80). Results indicated a statistically significant difference, with Intervention scoring significantly higher than Control, t(58) = 2.60, p = .012, d = 0.67. The mean difference (Intervention − Control) was 3.70, 95% CI [0.85, 6.55].
What each part does
- The test and the outcome tell the reader what was tested.
- The means and SDs give the direction. A reader can see Intervention scored higher before reading the statistics.
- The verdict sentence states significance and direction together.
- t(58) = 2.60, p = .012 is the test itself. With two groups of 30, df = 30 + 30 − 2 = 58.
- d = 0.67 says how big the difference is: moderate by Cohen's conventions. The p-value cannot tell you this.
- The mean difference and its 95% CI [0.85, 6.55] give the raw difference (3.70 points) and a range of plausible values for the population mean difference. The interval does not include zero, which agrees with the significant result. Naming it as the CI of the mean difference keeps readers from mistaking it for an interval around d.
If you used Welch's test
Welch's test changes the standard error and the degrees of freedom, so t, df, p and the CI all come from the "equal variances not assumed" row. This example uses unequal groups with different spreads.
| Group | M | SD | n |
|---|---|---|---|
| Intervention | 25.10 | 4.20 | 24 |
| Control | 21.00 | 7.80 | 36 |
A Welch's independent-samples t-test was conducted to compare wellbeing score between Intervention (M = 25.10, SD = 4.20) and Control (M = 21.00, SD = 7.80), as equal variances were not assumed. Results indicated a statistically significant difference, with Intervention scoring significantly higher than Control, t(55.96) = 2.63, p = .011, d = 0.62. The mean difference (Intervention − Control) was 4.10, 95% CI [0.98, 7.22].
For comparison, Student's test on the same data gives t(58) = 2.35, p = .022, 95% CI [0.61, 7.59]. That is why the row you report matters. Welch's df usually has decimals; report it to two decimal places. Cohen's d here uses the pooled standard deviation, the default in most software.
APA 7 formatting rules
| Rule | Correct | Incorrect |
|---|---|---|
| Italicise statistical symbols | t, p, M, SD, d | t, p, M, SD, d (not italic) |
| Report the exact p-value, to two or three decimals | p = .012 | p < .05 |
| Very small p-values use "less than" | p < .001 | p = .000 |
| No leading zero for values that cannot exceed 1 | p = .012 | p = 0.012 |
| Keep the leading zero for values that can exceed 1 | d = 0.67 | d = .67 |
| Round most statistics to two decimals | t(58) = 2.60 | t(58) = 2.6016 |
| Whole-number df for Student's test; two decimals for Welch's | t(55.96) = 2.63 | t(56) when Welch's test was used |
| Label the CI and give the order of subtraction | The mean difference (Intervention − Control) was 3.70, 95% CI [0.85, 6.55] | CI (0.85 – 6.55) |
SPSS prints "Sig. = .000" when p is very small. That never means p is zero, so report it as p < .001.
Reporting a non-significant result
A non-significant result is reported with the same values. Only the verdict changes. Sample data: Intervention M = 23.10, SD = 5.60; Control M = 21.40, SD = 5.90; 30 per group.
An independent-samples t-test was conducted to compare wellbeing score between Intervention (M = 23.10, SD = 5.60) and Control (M = 21.40, SD = 5.90). Although Intervention had a higher mean than Control, this descriptive difference was not statistically significant, t(58) = 1.14, p = .257, d = 0.30. The mean difference (Intervention − Control) was 1.70, 95% CI [−1.27, 4.67].
- Say the data did not provide sufficient evidence of a difference. Do not say the groups "were the same" or "did not differ"; a non-significant test does not show that.
- Still report d and the CI. Here the CI of the mean difference runs from Control scoring about 1.3 points higher to Intervention scoring about 4.7 points higher, which shows how uncertain the estimate is.
Common mistakes
- Writing p = .000. Report p < .001 instead.
- Reporting p without an effect size. p tells you whether the difference is statistically significant, not how large it is. Add Cohen's d.
- Leaving out the means and SDs. Without them the reader cannot see which group scored higher.
- Mixing up the output rows. If you report Welch's test, take t, df, p and the CI from the "equal variances not assumed" row, and say so.
- Leaving the CI unlabelled. Placed straight after d, an unlabelled CI can be read as an interval around d. Say it is the CI of the mean difference.
- Claiming cause. "The intervention improved wellbeing" goes beyond the test. Write "Intervention scored significantly higher", unless your design was a randomised experiment and your method section says so.
- Saying "proved". A significant result means a difference this large would be unlikely if the population means were equal. It is not proof.
- Calling a non-significant result "no difference". Say there was insufficient evidence of a difference.
What this guide doesn't include
This guide shows you the pattern using sample data. It can't work with your own results, so it doesn't give you:
- A paragraph written for your data. You fill in the templates yourself and check every value by hand.
- A check of your numbers. It can't tell you whether your t, p and confidence interval agree with each other, or warn you when something looks wrong.
- Cohen's d and the confidence interval if your software doesn't show them.
- A plain-English explanation and a chart of your own result.
- Answers to examiner questions about what your result does and doesn't show.
- The other 21 tests, from ANOVA to regression.
Want this for your own result?
For personalised output, use the Result Decoder. Enter the values from your SPSS, jamovi or R output and get your APA 7 paragraph, a check of your values, a plain-English explanation, charts and help defending your result.
Go to the Result DecoderBe ready to defend it
Supervisors and examiners rarely ask you to recite the numbers. They ask what the numbers allow you to claim. Three questions come up often for a t-test. Could you answer each one in a sentence, about your own result?
- "Why do you also need to report Cohen's d?"
- "Does this show the intervention caused the difference?"
- "Your result was not significant. Can you say the groups are the same?"
Practise with your own result
The Result Decoder's Defend this result panel asks questions like these about your own values, shows what your result does and doesn't support, and gives a suggested answer to compare with yours.
Try it with your resultFrequently asked questions
Do I report Student's or Welch's t-test?
Report the row your analysis used. If Levene's test is significant, or group sizes differ a lot, Welch's test is the safer choice, and many methodologists recommend it by default. Check what your supervisor or department expects.
Should I report a one-tailed p-value?
Only if you stated a directional hypothesis before collecting data. If you do, say "one-tailed" in the results paragraph.
Do I need the confidence interval?
APA 7 recommends reporting confidence intervals where possible. Report the 95% confidence interval of the mean difference alongside Cohen's d.
What if SPSS shows Sig. = .000?
Report p < .001. SPSS rounds very small p-values to .000, but the p-value is never exactly zero.
Can I put the results in a table instead?
Yes, especially when you run several t-tests. Keep a short sentence in the text that states the main finding.
More statistics guides
Browse all Statistics GuidesDecode your own result
Enter the values from your own SPSS, jamovi or R output to get your APA 7 paragraph, a plain-English explanation and charts, and to practise defending your result. Covers 22 tests for a one-time £15.99.