Selecting local models in multiple regression by maximizing power

DOI10.1007/S00184-008-0218-ZMaRDI QIDQ745341zbMATH OpenOpenAlexFDO

Authors Chad M. Schafer, Kjell A. Doksum

Publication date 14 October 2015

Published in Metrika (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/math/0612248, https://figshare.com/articles/journal_contribution/Selecting_Local_Models_in_Multiple_Regression_by_Maximizing_Power/6586883

zbMATH Keywords

curse of dimensionalitylocal linear regressiontestingbandwidth selectionefficacysignal to noise

Mathematics Subject Classification ID

Linear regression; mixed models (62J05)

Abstract: This paper considers multiple regression procedures for analyzing the relationship between a response variable and a vector of covariates in a nonparametric setting where both tuning parameters and the number of covariates need to be selected. We introduce an approach which handles the dilemma that with high dimensional data the sparsity of data in regions of the sample space makes estimation of nonparametric curves and surfaces virtually impossible. This is accomplished by abandoning the goal of trying to estimate true underlying curves and instead estimating measures of dependence that can determine important relationships between variables.

Recommendations

• LOCALIZED MODEL SELECTION FOR REGRESSION
• A criterion for local model selection
• Miscellanea. Local power of three classic criteria in generalised linear models with unknown dispersion
• scientific article; zbMATH DE number 2208162
• Model selection and local geometry
• Comparison of Local Power of Alternative Tests of Non-Nested Regression Models
• Model selection in regression under structural constraints

Cites work

• scientific article; zbMATH DE number 991833 (Why is no real title available?)
• scientific article; zbMATH DE number 1249686 (Why is no real title available?)
• scientific article; zbMATH DE number 5200048 (Why is no real title available?)
• A Closer Look at the Deviance
• Adaptive tests of regression functions via multiscale generalized likelihood ratios
• Comparing nonparametric versus parametric regression fits
• Component Identification and Estimation in Nonlinear High-Dimensional Regression Models by Structural Adaptation
• Design-adaptive Nonparametric Regression
• Generalized likelihood ratio statistics and Wilks phenomenon
• Geometrizing rates of convergence. II
• Geometrizing rates of convergence. III
• Goodness-of-fit tests for kernel regression with an application to option implied volatilities
• Graphical Comparison of Nonparametric Curves
• Local linear regression smoothers and their minimax efficiencies
• Minimax nonparametric detection of signals in white Gaussian noise
• Minimax nonparametric hypothesis testing: The case of an inhomogeneous alternative
• Multivariate locally weighted least squares regression
• Nonparametric estimation of global functionals and a measure of the explanatory power of covariates in regression
• Nonparametric model checks for regression
• Nonparametric smoothing and lack-of-fit tests
• On the use of nonparametric regression for model checking
• Optimal Kernel Weights Under a Power Criterion
• Propagation-separation approach for local likelihood estimation
• Testing for monotonicity of a regression mean by calibrating for linear functions.
• Testing for no effect in nonparametric regression

Cited in

(3)

• LOCALIZED MODEL SELECTION FOR REGRESSION
• Nonparametric variable selection and classification: the CATCH algorithm
• scientific article; zbMATH DE number 5200048 (Why is no real title available?)

This page was built for publication: Selecting local models in multiple regression by maximizing power

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q745341)