So sánh phương pháp

	Bootstrap Bayes (Rubin)	Bootstrap lặp (Double Bootstrap)	Kiểm định hoán vị (Ngẫu nhiên hóa)
Lĩnh vực	Thống kê	Thống kê	Thống kê
Họ	Regression model	Regression model	Regression model
Năm ra đời	1981	1986	2005
Người khởi xướng	Rubin (1981); large-sample theory by Lo (1987)	Hall (1986); Beran (1987)	Good (2005); Edgington & Onghena (2007); resampling tradition
Loại	Resampling / posterior simulation	Resampling calibration (nested bootstrap)	Nonparametric resampling test
Công trình gốc	Rubin, D. B. (1981). The Bayesian Bootstrap. The Annals of Statistics, 9(1), 130-134.	Hall, P. (1986). On the Bootstrap and Confidence Intervals. Annals of Statistics, 14(4), 1431-1452.	Good, P. (2005). Permutation, Parametric and Bootstrap Tests of Hypotheses (3rd ed.). Springer. ISBN: 978-0387202792
Tên gọi khác	Bayesian Bootstrap (Rubin), Rubin bootstrap, Dirichlet-weighted bootstrap	iterated bootstrap, nested bootstrap, calibrated bootstrap, Çift Bootstrap (Double / Iterated Bootstrap)	randomization test, exact permutation test, re-randomization test, Permütasyon Testi
Liên quan	5	5	5
Tóm tắt	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 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 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.