Bagging of Density Estimators

Abstract : In this work we give new density estimators by averaging classical density estimators such as the histogram, the frequency polygon and the kernel density estimators obtained over different bootstrap samples of the original data. We prove the L 2-consistency of these new estimators and compare them to several similar approaches by extensive simulations. Based on them, we give also a way to construct non parametric pointwise confidence intervals for the target density.
Document type :
Preprints, Working Papers, ...
2018
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01856183
Contributor : Jairo Cugliari <>
Submitted on : Thursday, August 9, 2018 - 11:08:05 PM
Last modification on : Friday, August 24, 2018 - 1:09:49 AM

Files

CBFP.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01856183, version 1
  • ARXIV : 1808.03447

Citation

Mathias Bourel, Jairo Cugliari. Bagging of Density Estimators. 2018. 〈hal-01856183v1〉

Share

Metrics

Record views

24

Files downloads

4