p-Value
Probability of seeing data at least as extreme as observed, if the null hypothesis were true. Small = H₀ unlikely.
Also known as: p-value, P-value, probability value
The p-value is the central decision figure of the classical hypothesis test. It answers the question: "Assuming H₀ is true — how likely are data at least as far from H₀ as those observed?"
- p < α → reject H₀ (effect statistically significant)
- p ≥ α → fail to reject H₀ (no evidence against H₀)
- Common thresholds: α = 0.05 (default), 0.01 (stricter), 0.001 (very strict)
See also
Used in
In the Algorithm Lab
Sources
- Wasserstein, R. L. & Lazar, N. A. — The ASA Statement on p-Values: Context, Process, and Purpose, The American Statistician, 70(2), 2016
- Fisher, R. A. — Statistical Methods for Research Workers, Oliver and Boyd, 1925
- Greenland, S. et al. — Statistical Tests, P Values, Confidence Intervals, and Power, European Journal of Epidemiology, 31(4), 2016