One-sample t test
The one-sample t test checks whether the mean of one variable differs from a fixed reference value (a norm, a target or a scale midpoint).
Menu: Analyze → Compare Means → One-Sample T Test…
When should I use One-sample t test?
- Comparing a sample mean with a known or hypothesised value, e.g. mean age vs 40.
What are the assumptions?
- Scale variable; observations independent.
- Approximately normal, or n ≥ 30 or so.
How do I run it in StatLab?
- Choose the test variable(s).
- Enter the test value.
How do I read the output?
| Output | Meaning |
|---|---|
| t, df, Sig. (2-tailed) | Test statistic, degrees of freedom (n − 1) and two-sided p-value. |
| Mean Difference and 95% CI | Sample mean minus the test value, with its confidence interval. If the CI excludes 0, p < .05. |
| Cohen's d | (mean − test value) / SD. |
Worked example
Test age against 40 in the bundled sample dataset (File → Sample dataset: 150 survey respondents with gender, programme group, age, pre/post test scores, five satisfaction items, income, smoking and education): mean = 41.25, t(149) = 1.01, p = .316.
How would I report it in APA style?
The mean age (M = 41.25, SD = 15.17) was not significantly different from 40 years, t(149) = 1.01, p = .316, d = 0.08.
Numbers above were computed by StatLab’s validated engine from the sample dataset when this page was built.
What are common mistakes?
- Concluding “the mean equals 40” from a non-significant result — absence of evidence is not evidence of equality.