On this page
What this lesson covers
Two-sample parametric tests compare population means using either independent samples with pooled variance or matched observations analyzed as paired differences.
Choose a pooled t-test for independent normal samples with equal unknown variances. Use a paired test when observations belong together, taking variability from the differences themselves.
How do you calculate independent-samples and paired t-statistics?
For independent samples, divide the difference in sample means minus the hypothesized difference by the pooled standard error. For matched data, first compute each pair’s difference, then test its mean using the standard deviation of those differences.
Independent-samples t = (difference in means − hypothesized difference) / √(pooled variance/n1 + pooled variance/n2)
- Sample means
- Hypothesized difference in population means
- Pooled estimate of the common population variance
- Independent sample sizes
Paired t = (mean difference − hypothesized mean difference) / (standard deviation of differences / √n)
- Mean of matched differences
- Hypothesized mean difference
- Sample standard deviation of differences
- Number of matched pairs
For example, Strategy Q and its benchmark are matched month by month for 144 months. Assuming approximately normal differences, their strategy-minus-benchmark mean difference is 0.24% per month with sample standard deviation 1.2%. For a hypothesized difference of zero, SE = 1.2% / √144 = 0.1% and paired t = 0.24% / 0.1% = 2.4, with 143 degrees of freedom.
Common mistakes
- Treating naturally paired monthly returns as independent samples ignores the month-by-month pairing.
Try a practice question
Choose an answer, then check it to read the explanation for every option.
Continue studying in Quizara
In Quizara the lesson comes with more practice questions on the topic, explanations for every option and an AI tutor for your follow-up questions.
Written by the Quizara Editorial Team under our editorial standards.