Some nonasymptotic results on resampling in high dimension, I: Confidence regions
Authors:
Open Access
- 1 February 2010
- journal article
- research article
- Published by Institute of Mathematical Statistics in The Annals of Statistics
- Vol. 38 (1) , 51-82
Abstract
We study generalized bootstrap confidence regions for the mean of a random vector whose coordinates have an unknown dependency structure. The random vector is supposed to be either Gaussian or to have a symmetric and bounded distribution. The dimensionality of the vector can possibly be much larger than the number of observations and we focus on a nonasymptotic control of the confidence level, following ideas inspired by recent results in learning theory. We consider two approaches, the first based on a concentration principle (valid for a large class of resampling weights) and the second on a resampled quantile, specifically using Rademacher weights. Several intermediate results established in the approach based on concentration principles are of interest in their own right. We also discuss the question of accuracy when using Monte Carlo approximations of the resampled quantities.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Some nonasymptotic results on resampling in high dimension, II: Multiple testsThe Annals of Statistics, 2010
- Coherent neural representation of hand speed in humans revealed by MEG imagingProceedings of the National Academy of Sciences, 2007
- Exact and Approximate Stepdown Methods for Multiple Hypothesis TestingJournal of the American Statistical Association, 2005
- The Impact of the Bootstrap on Statistical Algorithms and TheoryStatistical Science, 2003
- Random rates in anisotropic regression (with a discussion and a rejoinder by the authors)The Annals of Statistics, 2002
- Rademacher penalties and structural risk minimizationIEEE Transactions on Information Theory, 2001
- On General Resampling Algorithms and their Performance in Distribution EstimationThe Annals of Statistics, 1994
- Exchangeably Weighted Bootstraps of the General Empirical ProcessThe Annals of Probability, 1993
- A Rank Statistics Approach to the Consistency of a General BootstrapThe Annals of Statistics, 1992
- Honest Confidence Regions for Nonparametric RegressionThe Annals of Statistics, 1989