Nonparametric regression with the scale depending on auxiliary variable

DOI10.1214/13-AOS1126zbMATH Open1292.62057arXiv1308.2809MaRDI QIDQ366996FDOQ366996

Authors: Sam Efromovich 

Publication date: 25 September 2013

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: The paper is devoted to the problem of estimation of a univariate component in a heteroscedastic nonparametric multiple regression under the mean integrated squared error (MISE) criteria. The aim is to understand how the scale function should be used for estimation of the univariate component. It is known that the scale function does not affect the rate of the MISE convergence, and as a result sharp constants are explored. The paper begins with developing a sharp-minimax theory for a pivotal model $Y=f(X)+sigma(X,mathbfZ)varepsilon$, where $varepsilon$ is standard normal and independent of the predictor X and the auxiliary vector-covariate $mathbfZ$. It is shown that if the scale $sigma(x,mathbfz)$ depends on the auxiliary variable, then a special estimator, which uses the scale (or its estimate), is asymptotically sharp minimax and adaptive to unknown smoothness of f(x). This is an interesting conclusion because if the scale does not depend on the auxiliary covariate $mathbfZ$, then ignoring the heteroscedasticity can yield a sharp minimax estimation. The pivotal model serves as a natural benchmark for a general additive model $Y=f(X)+g(mathbfZ)+sigma(X,mathbfZ)varepsilon$, where $varepsilon$ may depend on $(X,mathbfZ)$ and have only a finite fourth moment. It is shown that for this model a data-driven estimator can perform as well as for the benchmark. Furthermore, the estimator, suggested for continuous responses, can be also used for the case of discrete responses. Bernoulli and Poisson regressions, that are inherently heteroscedastic, are particular considered examples for which sharp minimax lower bounds are obtained as well. A numerical study shows that the asymptotic theory sheds light on small samples.

Full work available at URL: https://arxiv.org/abs/1308.2809

Recommendations

• scientific article; zbMATH DE number 947421
• Adaptive estimation in a heteroscedastic nonparametric regression
• Univariate Nonparametric Regression in the Presence of Auxiliary Covariates
• Adaptive estimators for nonparametric heteroscedastic regression models
• On a robust local estimator for the scale function in heteroscedastic nonparametric regression

zbMATH Keywords

adaptationlower boundMISEsharp minimax

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic distribution theory in statistics (62E20) General considerations in statistical decision theory (62C05)

Cites Work

• Exact mean integrated squared error
• Approximation Theorems of Mathematical Statistics
• Title not available (Why is that?)
• Title not available (Why is that?)
• Additive regression and other nonparametric models
• Nonlinear time series. Nonparametric and parametric methods
• Sequential Nonparametric Estimation of a Density
• Design-adaptive Nonparametric Regression
• Title not available (Why is that?)
• All of Nonparametric Statistics
• Nonparametric estimation of the anisotropic probability density of mixed variables
• Nonparametric curve estimation. Methods, theory, and applications
• Optimal estimation in additive regression models
• Variable selection in nonparametric additive models
• Semiparametric and nonparametric methods in econometrics
• Title not available (Why is that?)
• Optimal filtering of square-integrable signals in Gaussian noise
• Asymptotic minimax estimation of regression in the additive model
• Random rates in anisotropic regression. (With discussion)
• Variance function estimation in multivariate nonparametric regression with fixed design
• Title not available (Why is that?)
• Title not available (Why is that?)
• Nonparametric Estimation of a Density of Unknown Smoothness
• LAN in Problems of Nonparametric Estimation of Functions and Lower Bounds for Quadratic Risks
• Wavelet threshold estimation for additive regression models
• On nonparametric regression for iid observations in a general setting
• On sharp adaptive estimation of multivariate curves
• Fejér means for multivariate Fourier series
• Nonparametric estimation of an additive model with a link function
• Optimal nonparametric estimation of the density of regression errors with finite support
• Nonparametric regression with the scale depending on auxiliary variable
• Title not available (Why is that?)
• Fourier series in several variables
• Estimation in additive models with highly or non-highly correlated covariates

Cited In (7)

• Statistical inference in sparse high-dimensional additive models
• Univariate Nonparametric Regression in the Presence of Auxiliary Covariates
• Conditional hazard rate estimation for right censored data
• Nonparametric regression with responses missing at random and the scale depending on auxiliary covariates
• Nonparametric regression with the scale depending on auxiliary variable
• Penalized least squares estimation in the additive model with different smoothness for the components
• Sequential nonparametric estimation of controlled multivariate regression

This page was built for publication: Nonparametric regression with the scale depending on auxiliary variable

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q366996)