Paired t-test
Hypothesis tests · Method and input reference
Two-sided; independent t uses Welch. Paired tests require matched observations. Permutation uses difference in means, 9,999 resamples and a fixed seed. Effect sizes use pooled sample SD. Synthetic example: 120 matched baseline and week-12 blood pressures (mmHg). Row positions identify the same person; responses vary and some worsen.
Open calculator · Compare methods in the decision matrix
When to consider it
- Two dependent observations per unit, continuous outcome with approximately normal differences.
Assumptions and scope
- Each observation must be matched to the same subject or unit in the other sample.
- Pairs must be independent. Assess the distribution of within-pair differences, especially with small samples.
Required inputs
- Observations — Numeric observations; preserve the row and column structure described above.
- Second sample — Numeric observations; preserve the row and column structure described above.
Review missing values and data coding before running. Sample inputs are synthetic teaching examples.
Implementation
Lifescio validates inputs and formats results; listed functions are the principal calculation routines, not an exhaustive transitive dependency list.
- scipy 1.15.3: scipy.stats.ttest_rel
These are pinned library versions; saved results record the versions actually used at runtime.