Inhomogeneous and Anisotropic Conditional Density Estimation from Dependent Data

Abstract : The problem of estimating a conditional density is considered. Given a collection of partitions, we propose a procedure that selects from the data the best partition among that collection and then provides the best piecewise polynomial estimator built on that partition. The observations are not supposed to be independent but only $\beta$-mixing; in particular, our study includes the estimation of the transition density of a Markov chain. For a well-chosen collection of possibly irregular partitions, we obtain oracle-type inequalities and adaptivity results in the minimax sense over a wide range of possibly anisotropic and inhomogeneous Besov classes. We end with a short simulation study.
Document type :
Journal articles
Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2011, 5, pp.1618-1653. 〈10.1214/11-EJS653〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00557307
Contributor : Claire Lacour <>
Submitted on : Monday, November 28, 2011 - 3:42:30 PM
Last modification on : Monday, May 29, 2017 - 2:22:12 PM
Document(s) archivé(s) le : Wednesday, February 29, 2012 - 2:26:59 AM

File

RevdenscondinhomogeneEJS.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Nathalie Akakpo, Claire Lacour. Inhomogeneous and Anisotropic Conditional Density Estimation from Dependent Data. Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2011, 5, pp.1618-1653. 〈10.1214/11-EJS653〉. 〈hal-00557307v2〉

Share

Metrics

Record views

428

Document downloads

166