T-test

T-test (Student's T-test)

A statistical test for comparing the means of two groups — determines whether an observed difference is likely real or could have occurred by random chance.

When you'd see it: A/B test analysis, before-after comparisons, clinical trials. 'We ran a T-test and the result was significant' means the two groups' means are different enough that random variation is an unlikely explanation.

Why it matters: The T-test is the standard tool for the most common analytical question in business: did these two groups actually perform differently? It accounts for sample size and variability — a 5% difference is more credible with 10,000 observations than with 30.

Common mistakes: Using a T-test when assumptions aren't met. T-tests assume approximately normally distributed data and similar variance between groups. For very non-normal distributions or ordinal data, a non-parametric test like Mann-Whitney U is more appropriate.

Related ANOVA, P-value, confidence interval, statistical significance, null hypothesis