PCA-kernel estimation

DOI10.1524/STRM.2012.1084MaRDI QIDQ3224135zbMATH OpenOpenAlexFDO

Authors Gérard Biau, André Mas

Publication date 29 March 2012

Published in Statistics & Risk Modeling (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1003.5089

zbMATH Keywords

density estimationdimension reductionprincipal component analysisregression estimationnonparametric kernel estimation

Mathematics Subject Classification ID

Density estimation (62G07) Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Factor analysis and principal components; correspondence analysis (62H25)

Abstract: Many statistical estimation techniques for high-dimensional or functional data are based on a preliminary dimension reduction step, which consists in projecting the sample $$ onto the first $D$ eigenvectors of the Principal Component Analysis (PCA) associated with the empirical projector $hatP{i}_D$. Classical nonparametric inference methods such as kernel density estimation or kernel regression analysis are then performed in the (usually small) $D$-dimensional space. However, the mathematical analysis of this data-driven dimension reduction scheme raises technical problems, due to the fact that the random variables of the projected sample $$ are no more independent. As a reference for further studies, we offer in this paper several results showing the asymptotic equivalencies between important kernel-related quantities based on the empirical projector and its theoretical counterpart. As an illustration, we provide an in-depth analysis of the nonparametric kernel regression case

Recommendations

• High-dimensional principal projections
• On the predictive potential of kernel principal components
• Statistical properties of kernel principal component analysis
• Efficient estimation of linear functionals of principal components
• Kernel-based functional principal components

Cites work

• Asymptotic theory for the principal component analysis of a vector random function: Some applications to statistical inference
• CLT in functional linear regression models
• Defining probability density for a distribution of random functions
• Exploratory Projection Pursuit
• Local linear regression smoothers and their minimax efficiencies
• On Estimation of a Probability Density Function and Mode
• Optimal global rates of convergence for nonparametric regression
• Optimal rates of convergence for nonparametric estimators
• Remarks on Non-Parametric Estimates for Density Functions and Regression Curves
• Remarks on Some Nonparametric Estimates of a Density Function

Cited in

(12)

• Statistical analysis and parameter selection for Mapper
• PCA-based dimension reduction for splines
• A note on kernel principal component regression
• Accuracy of suboptimal solutions to kernel principal component analysis
• On the predictive potential of kernel principal components
• Revisiting the predictive power of kernel principal components
• Kernel Principal Component Analysis: Applications, Implementation and Comparison
• High-dimensional principal projections
• Kernel principal component analysis for efficient, differentiable parametrization of multipoint geostatistics
• The correction term in a small-ball probability factorization for random curves
• Statistical analysis of Mapper for stochastic and multivariate filters
• Nonparametric modelling for functional data: selected survey and tracks for future

This page was built for publication: PCA-kernel estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3224135)