Lesson 9 of 12Article20 min
Hypothesis Testing & p-Values
State H₀ (status quo) and Hₐ (research claim). Compute a test statistic measuring how weird the data are under H₀. The p-value is the probability, under H₀, of data at least as extreme as observed.
The logic of falsification
State H₀ (status quo) and Hₐ (research claim). Compute a test statistic measuring how weird the data are under H₀. The p-value is the probability, under H₀, of data at least as extreme as observed.
- Small p-value → data incompatible with H₀ (at conventional α like 0.05).
- Failing to reject ≠ proving H₀ true.
- p-hacking and multiple comparisons inflate false discoveries.
Always report effect size and CI alongside the p-value — significance ≠ importance.