Σύγκριση μεθόδων

	Wild Bootstrap για Συμπερασματολογία σε Παλινδρόμηση	Block Bootstrap (Moving Block και Stationary)	Επαγωγή Bootstrap
Πεδίο	Στατιστική	Στατιστική	Στατιστική
Οικογένεια	Regression model	Regression model	Regression model
Έτος προέλευσης	1986	1989	1979
Δημιουργός	Wu (1986); refined by Davidson & Flachaire (2008)	Künsch (moving block, 1989); Politis & Romano (stationary, 1994)	Bradley Efron
Τύπος	Resampling-based regression inference	Resampling inference for dependent data	Resampling-based inference
Θεμελιώδης πηγή	Wu, C. F. J. (1986). Jackknife, Bootstrap and Other Resampling Methods in Regression Analysis. Annals of Statistics, 14(4), 1261-1295.	Künsch, H. R. (1989). The Jackknife and the Bootstrap for General Stationary Observations. Annals of Statistics, 17(3), 1217-1241.	Efron, B. (1979). Bootstrap Methods: Another Look at the Jackknife. Annals of Statistics, 7(1), 1-26.
Εναλλακτικές ονομασίες	wild bootstrap, wild cluster bootstrap, Wu-Liu resampling, Wild Bootstrap	moving block bootstrap, stationary bootstrap, blok bootstrap (moving block / stationary)	bootstrap, bootstrap resampling, nonparametric bootstrap, Bootstrap Çıkarımı
Συναφείς	5	5	5
Σύνοψη	The wild bootstrap is a resampling method for regression models with heteroscedastic errors, introduced by Wu (1986) and refined by Davidson and Flachaire (2008). It builds a bootstrap distribution by rescaling each fitted residual with a random sign, so that standard errors and confidence intervals stay valid when the error variance is not constant or the data are clustered.	Block bootstrap is a resampling method for dependent, autocorrelated time-series data: instead of resampling single observations, it resamples whole blocks of consecutive observations so the serial-correlation structure is preserved. The moving block variant was introduced by Künsch (1989) and the stationary variant by Politis and Romano (1994).	Bootstrap inference, introduced by Bradley Efron in 1979, estimates the sampling distribution of a statistic by repeatedly resampling the observed data with replacement. It requires no distributional assumption and produces reliable confidence intervals even in small samples.