Resampling-Based Confidence Regions and Multiple Tests for a Correlated Random Vector

Abstract

We study generalized bootstrapped confidence regions for the mean of a random vector whose coordinates have an unknown dependence structure, with a non-asymptotic control of the confidence level. The random vector is supposed to be either Gaussian or to have a symmetric bounded distribution. We consider two approaches, the first based on a concentration principle and the second on a direct boost-rapped quantile. The first one allows us to deal with a very large class of resampling weights while our results for the second are restricted to Rademacher weights. However, the second method seems more accurate in practice. Our results are motivated by multiple testing problems, and we show on simulations that our procedures are better than the Bonferroni procedure (union bound) as soon as the observed vector has sufficiently correlated coordinates.

Cite

Text

Arlot et al. "Resampling-Based Confidence Regions and Multiple Tests for a Correlated Random Vector." Annual Conference on Computational Learning Theory, 2007. doi:10.1007/978-3-540-72927-3_11

Markdown

[Arlot et al. "Resampling-Based Confidence Regions and Multiple Tests for a Correlated Random Vector." Annual Conference on Computational Learning Theory, 2007.](https://mlanthology.org/colt/2007/arlot2007colt-resampling/) doi:10.1007/978-3-540-72927-3_11

BibTeX

@inproceedings{arlot2007colt-resampling,
  title     = {{Resampling-Based Confidence Regions and Multiple Tests for a Correlated Random Vector}},
  author    = {Arlot, Sylvain and Blanchard, Gilles and Roquain, Étienne},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2007},
  pages     = {127-141},
  doi       = {10.1007/978-3-540-72927-3_11},
  url       = {https://mlanthology.org/colt/2007/arlot2007colt-resampling/}
}