Student's t-test is one of the most widely used statistical tests. It tests whether the mean of a group differs from a reference value (one-sample), or whether two groups have significantly different means (independent or paired).
When to use it
Compare an observed mean to a theoretical value (one-sample)
Compare two independent groups (e.g. treatment vs placebo)
Compare before/after measurements on the same subjects (paired)
Requirements
Continuous dependent variable
Approximately normal distribution (or n > 30)
Welch's t-test available when variances are unequal
What StatsLab computes
t statistic and degrees of freedom
p-value (two-tailed and one-tailed)
95% CI of the mean difference
Effect size d (Cohen)
Descriptive statistics per group
Visualization with 95% CI
Worked example
Context : Comparing cognitive scores between a supplementation group (n=25) and a control group (n=25).
Result : t(48) = 2.34, p = 0.023, d = 0.66
Interpretation : Significant difference (p < 0.05). The supplemented group scores higher. The moderate effect size (d = 0.66) indicates a clinically meaningful effect.