Smoothing splines with varying smoothing parameter

DOI10.1093/BIOMET/AST031MaRDI QIDQ2870258zbMATH OpenOpenAlexFDO

Authors Pang Du, Jinglai Shen, Xiao Wang

Publication date 17 January 2014

Published in Biometrika (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1306.1868

zbMATH Keywords

equivalent kernelsGreen's functionnonparametric regressionsmoothing splinesspatially adaptive smoothing

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Numerical computation using splines (65D07)

Abstract: This paper considers the development of spatially adaptive smoothing splines for the estimation of a regression function with non-homogeneous smoothness across the domain. Two challenging issues that arise in this context are the evaluation of the equivalent kernel and the determination of a local penalty. The roughness penalty is a function of the design points in order to accommodate local behavior of the regression function. It is shown that the spatially adaptive smoothing spline estimator is approximately a kernel estimator. The resulting equivalent kernel is spatially dependent. The equivalent kernels for traditional smoothing splines are a special case of this general solution. With the aid of the Green's function for a two-point boundary value problem, the explicit forms of the asymptotic mean and variance are obtained for any interior point. Thus, the optimal roughness penalty function is obtained by approximately minimizing the asymptotic integrated mean square error. Simulation results and an application illustrate the performance of the proposed estimator.

Recommendations

• Smoothing splines with variable continuity properties and degree
• Smoothing variational splines
• Smoothing Spline Estimation in Varying-Coefficient Models
• Spline smoothing with an estimated order parameter
• Multivariate Smoothing Spline Functions
• scientific article; zbMATH DE number 4011660
• Semiparametric smoothing splines
• scientific article; zbMATH DE number 46694

Cited in

(23)

• Spatially adaptive splines for statistical linear inverse problems
• Adaptive penalized splines for data smoothing
• Local roughness penalties for regression splines
• Adaptive spline fitting with particle swarm optimization
• Identifying local smoothness for spatially inhomogeneous functions
• Asymptotic optimality of a multivariate version of the generalized cross validation in adaptive smoothing splines
• Enhancement of spatially adaptive smoothing splines via parameterization of smoothing parameters
• Adaptive piecewise polynomial estimation via trend filtering
• Approximating data with weighted smoothing splines
• Variance reduction in smoothing splines
• Data driven adaptive spline smoothing
• Smoothing Spline Score Estimation
• Hybrid Adaptive Splines
• Smoothing Splines Approximation Using Hilbert Curve Basis Selection
• Estimating functions and derivatives via adaptive penalized splines
• scientific article; zbMATH DE number 7300702 (Why is no real title available?)
• Low‐Rank Smoothing Splines on Complicated Domains
• Spatially adaptive smoothing splines
• Lévy Adaptive B-spline Regression via Overcomplete Systems
• Adaptive smoothing spline estimator for the function-on-function linear regression model
• Smoothly varying regularization
• Deep neural networks are adaptive to function regularity and data distribution in approximation and estimation
• Generalized profiling estimation for global and adaptive penalized spline smoothing

This page was built for publication: Smoothing splines with varying smoothing parameter

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2870258)