Comparer des méthodes

	Corrélation versus Causalité	Taille de l'effet
Domaine	Statistiques de recherche	Statistiques de recherche
Famille	Process / pipeline	Process / pipeline
Année d'origine	1965	1988
Auteur d'origine	Multiple sources (Bradford Hill, Judea Pearl, Donald Rubin)	Jacob Cohen
Type	Concept	Concept
Source fondatrice	Pearl, J. (2009). Causality: Models, Reasoning, and Inference (2nd ed.). Cambridge University Press. ISBN: 978-0-521-89560-6	Cohen, J. (1988). Statistical Power Analysis for the Behavioral Sciences (2nd ed.). Lawrence Erlbaum Associates. ISBN: 0-8058-0283-5
Alias	correlation and causation, causal inference, spurious correlation, confounding	ES, Cohen's d, standardized effect, practical significance
Apparentées	4	4
Résumé	Correlation measures the strength and direction of association between two variables; causation implies that changes in one variable directly produce changes in another. A strong correlation (e.g., r = 0.9) does not prove causation. Classic examples abound: shoe size and reading ability are correlated in children (confounded by age), but shoe size does not cause reading ability. Understanding when correlation implies causation requires evaluating study design, confounding variables, temporal precedence, and mechanism. Randomized experiments offer the strongest causal evidence; observational studies must carefully control for confounders.	Effect size quantifies the magnitude of a research finding independent of sample size. While a p-value tells you whether a result is statistically significant, an effect size tells you how big the result is. Jacob Cohen formalized effect size measurement in behavioral sciences (1988), establishing standard benchmarks (small = 0.2, medium = 0.5, large = 0.8 for Cohen's d). Effect sizes are essential for meta-analysis, power analysis, and communicating the practical importance of research findings.