Comparer des méthodes

	Bootstrap itéré	Le Bootstrap Bayésien (Rubin)	Test par permutation (ou randomisation)
Domaine	Statistique	Statistique	Statistique
Famille	Regression model	Regression model	Regression model
Année d'origine	1986	1981	2005
Auteur d'origine	Hall (1986); Beran (1987)	Rubin (1981); large-sample theory by Lo (1987)	Good (2005); Edgington & Onghena (2007); resampling tradition
Type	Resampling calibration (nested bootstrap)	Resampling / posterior simulation	Nonparametric resampling test
Source fondatrice	Hall, P. (1986). On the Bootstrap and Confidence Intervals. Annals of Statistics, 14(4), 1431-1452.	Rubin, D. B. (1981). The Bayesian Bootstrap. The Annals of Statistics, 9(1), 130-134.	Good, P. (2005). Permutation, Parametric and Bootstrap Tests of Hypotheses (3rd ed.). Springer. ISBN: 978-0387202792
Alias	iterated bootstrap, nested bootstrap, calibrated bootstrap, Çift Bootstrap (Double / Iterated Bootstrap)	Bayesian Bootstrap (Rubin), Rubin bootstrap, Dirichlet-weighted bootstrap	randomization test, exact permutation test, re-randomization test, Permütasyon Testi
Apparentées	5	5	5
Résumé	The double bootstrap is a resampling method that calibrates a bootstrap confidence interval with a second, nested layer of bootstrap to bring its actual coverage closer to the nominal level. Introduced by Hall (1986) and Beran (1987), it is especially valuable for small samples and skewed distributions where a single-layer bootstrap under-covers.	The Bayesian Bootstrap, introduced by Donald B. Rubin in 1981, is a resampling method that produces a Bayesian counterpart to the frequentist bootstrap by assigning each observation a random weight drawn from a Dirichlet distribution. It yields a full posterior distribution for a statistic and allows prior information to be incorporated.	The permutation test is a nonparametric resampling procedure that builds the sampling distribution of a test statistic directly from the data by repeatedly shuffling the group labels. Developed in the resampling tradition and treated systematically by Good (2005) and Edgington & Onghena (2007), it requires no parametric distributional assumption and yields an exact p-value.