T-Test Calculator

Which t-test should you use?

• Independent samples: compares the means of two separate groups, for example men and women or treatment and control.
• Paired samples: compares two measurements on the same people, such as before and after a training programme.
• One sample: compares the mean of one group with a known or target value.

Welch or pooled?

The pooled test assumes both groups have the same variance. Welch’s test does not, and it performs well even when variances are equal, so it is the safer default and the one selected here. Our hypothesis testing service covers t-tests, ANOVA and non-parametric tests.

Assumptions to check

• Observations are independent, except for the pairing in a paired test.
• The outcome is numeric, and roughly normal in each group, or the sample is reasonably large.
• There are no extreme outliers.

If the data are clearly skewed or ordinal, consider the Mann-Whitney U test or the Wilcoxon signed-rank test. Our test finder can help you decide.

Reporting the result

A complete report gives the t value, degrees of freedom, p-value, the mean difference with its confidence interval, and an effect size such as Cohen’s d. For example: t(16.6) = 3.81, p = 0.002, mean difference = 3.9, 95% CI [1.73, 6.07], d = 1.70.

Related analysis services

We run t-tests and related comparisons through hypothesis testing and SPSS and STATA analysis, and present the results as clear tables, charts and written summaries. See all services or tell us about your project.