EUVIMEDEUVIMED entdecken
Crossref

Non parametric regression function estimation in presence of common noise

F. Comte, V. Genon-Catalot

Annals of the Institute of Statistical Mathematics · 17.04.2026

DOI: 10.1007/s10463-026-00975-y ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annals of the Institute of Statistical Mathematics, online erschienen am 17.04.2026. Verfasst von F. Comte und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

. Consider the regression model ( Y i = b ( X i ) + u i , i = 1 , . . . , n ) with error process u i = √ ρε 0 + √ 1 − ρε i where ( ε i , i = 0 , . . . , n ) are independent centered random variables (r.v.) with unit variance and ( X 1 , . . . , X n ) are independent and identically distributed r.v. independent of ( ε i , i = 0 , . . . , n ) . Thus there is a common noise ε 0 to all u i ’s. We study the nonparametric estimation of the regression function b on a subset A ⊂ R from the observations ( X i , Y i , , i = 1 , . . . , n ) using a projection method on sieves. The standard least-squares contrast fails to provide consistent estimators. Therefore, we introduce a least-squared contrast taking into account the covariance matrix of the noise. By minimizing the contrast over a finite dimensional subspace S m of L 2 ( A, dx ) , we obtain a projection estimator and study its risk measured either as the expectation of the empirical norm or as the expectation of the theoretical norm associated with the contrast. In the latter case, we study a trimmed estimator. The risk bounds have a variance term with the usual rate. A specific difficulty occurs for proving that the empirical and the theoretical norms are equivalent for functions of S m . The estimators are implemented on simulated data and show excellent performances when E b ( X 1 ) is known as this parameter is not identifiable from the model.

Zitieren

APA

Comte, F., & Genon-Catalot, V. (2026). Non parametric regression function estimation in presence of common noise. Annals of the Institute of Statistical Mathematics. https://doi.org/10.1007/s10463-026-00975-y

Vancouver

Comte F, Genon-Catalot V. Non parametric regression function estimation in presence of common noise. Annals of the Institute of Statistical Mathematics. 2026. doi:10.1007/s10463-026-00975-y

BibTeX
@article{Comte2026,
  author = {Comte, F. and Genon-Catalot, V.},
  title = {Non parametric regression function estimation in presence of common noise},
  journal = {Annals of the Institute of Statistical Mathematics},
  year = {2026},
  doi = {10.1007/s10463-026-00975-y}
}
Kostenlos starten →