Methodology and theory for partial least squares applied to functional data

Abstract

The partial least squares procedure was originally developed to estimate the slope parameter in multivariate parametric models. More recently it has gained popularity in the functional data literature. There, the partial least squares estimator of slope is either used to construct linear predictive models, or as a tool to project the data onto a one-dimensional quantity that is employed for further statistical analysis. Although the partial least squares approach is often viewed as an attractive alternative to projections onto the principal component basis, its properties are less well known than those of the latter, mainly because of its iterative nature. We develop an explicit formulation of partial least squares for functional data, which leads to insightful results and motivates new theory, demonstrating consistency and establishing convergence rates.

Published in at http://dx.doi.org/10.1214/11-AOS958 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (4)

• Prediction in functional linear regression
• Penalized Partial Least Squares Based on B-Splines Transformations
• The smallest eigenvalue of Hankel matrices
• Varying-coefficient functional linear regression

Cited by in corpus (23)

• Estimation in functional linear quantile regression
• Optimal Penalized Function-on-Function Regression under a Reproducing Kernel Hilbert Space Framework
• On the use of reproducing kernel Hilbert spaces in functional classification
• Functional linear regression with points of impact
• Wavelet-domain regression and predictive inference in psychiatric neuroimaging
• Variable selection in functional data classification: a maxima-hunting proposal
• Multi-dimensional Functional Principal Component Analysis
• Conditional Independence Testing in Hilbert Spaces with Applications to Functional Data Analysis
• Sparse semiparametric regression when predictors are mixture of functional and high-dimensional variables
• Multi-class classification of biomechanical data: A functional LDA approach based on multi-class penalized functional PLS
• PLS: a new statistical insight through the prism of orthogonal polynomials
• Functional continuum regression
• An Alternative Approach to Functional Linear Partial Quantile Regression
• PCA-based estimation for functional linear regression with functional responses
• On convergence of general wavelet decompositions of nonstationary stochastic processes
• Sparse Wavelet Estimation in Quantile Regression with Multiple Functional Predictors
• A simple method to construct confidence bands in functional linear regression
• Partial least squares for sparsely observed curves with measurement errors
• Local Optimization of Black-Box Function with High or Infinite-Dimensional Inputs
• Profile Estimation for Partial Functional Partially Linear Single-Index Model
• Partial least squares for dependent data
• Partial Least Squares for Functional Joint Models
• Fast implementation of partial least squares for function-on-function regression