A robust partial least squares approach for function-on-function regression

DOI10.1214/21-BJPS523zbMATH Open1503.62039arXiv2111.01238OpenAlexW3209633008MaRDI QIDQ82006FDOQ82006

Han Lin Shang, Ufuk Beyaztas

Publication date: 1 November 2021

Published in: Brazilian Journal of Probability and Statistics (Search for Journal in Brave)

Abstract: The function-on-function linear regression model in which the response and predictors consist of random curves has become a general framework to investigate the relationship between the functional response and functional predictors. Existing methods to estimate the model parameters may be sensitive to outlying observations, common in empirical applications. In addition, these methods may be severely affected by such observations, leading to undesirable estimation and prediction results. A robust estimation method, based on iteratively reweighted simple partial least squares, is introduced to improve the prediction accuracy of the function-on-function linear regression model in the presence of outliers. The performance of the proposed method is based on the number of partial least squares components used to estimate the function-on-function linear regression model. Thus, the optimum number of components is determined via a data-driven error criterion. The finite-sample performance of the proposed method is investigated via several Monte Carlo experiments and an empirical data analysis. In addition, a nonparametric bootstrap method is applied to construct pointwise prediction intervals for the response function. The results are compared with some of the existing methods to illustrate the improvement potentially gained by the proposed method.

Full work available at URL: https://arxiv.org/abs/2111.01238

Recommendations

• A partial least squares approach for function-on-function interaction regression
• Robust functional linear regression based on splines
• Robust functional regression based on principal components
• Fast implementation of partial least squares for function-on-function regression
• Robust estimation for semi-functional linear regression models

zbMATH Keywords

dimension reductionbasis functionSIMPLSweighted likelihood

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Nonparametric robustness (62G35) Factor analysis and principal components; correspondence analysis (62H25) Linear regression; mixed models (62J05) Nonparametric statistical resampling methods (62G09) Functional data analysis (62R10)

Cites Work

• Nonparametric functional data analysis. Theory and practice.
• A partial overview of the theory of statistics with functional data
• Inference for functional data with applications
• Forecasting with unequally spaced data by a functional principal component approach
• Efficiency versus robustness: The case for minimum Hellinger distance and related methods
• Applied functional data analysis. Methods and case studies
• Semiparametric quantile estimation for varying coefficient partially linear measurement errors models
• Robust functional linear regression based on splines
• A partial least squares approach for function-on-function interaction regression
• Nonparametric discrimination of areal functional data
• Robust functional regression based on principal components
• Penalized function-on-function regression
• Dynamic data analysis. Modeling data with differential equations
• Forecasting functional time series
• Multivariate functional linear regression and prediction
• Title not available (Why is that?)
• Robust statistical inference: weighted likelihoods or usual m-estimation?
• Title not available (Why is that?)
• Interaction Model and Model Selection for Function-on-Function Regression
• Title not available (Why is that?)
• Linear mixed function‐on‐function regression models
• Functional Principal Component Regression and Functional Partial Least Squares
• Title not available (Why is that?)
• Methodology and theory for partial least squares applied to functional data
• Introduction to Functional Data Analysis
• Nonparametric density estimation for functional data by delta sequences
• Forecasting functional time series using weighted likelihood methodology
• Theoretical Foundations of Functional Data Analysis, with an Introduction to Linear Operators
• Functional Additive Models
• On Properties of Functional Principal Components Analysis
• Title not available (Why is that?)
• Title not available (Why is that?)
• 8. Functional Data Analysis
• Smoothing noisy data with spline functions
• Functional Principal Component Regression and Functional Partial Least‐squares Regression: An Overview and a Comparative Study
• Detection of outliers in functional time series
• Functional linear regression via canonical analysis
• Recent developments in complex and spatially correlated functional data
• PLS regression on a stochastic process
• Functional linear regression analysis for longitudinal data

Cited In (4)

• Robust estimation for varying coefficient partially functional linear regression models based on exponential squared loss function
• Locally sparse and robust partial least squares in scalar-on-function regression
• Restricted function‐on‐function linear regression model
• robflreg

Uses Software

• Rainbow
• fda (R)
• wle
• expm
• WRS2

This page was built for publication: A robust partial least squares approach for function-on-function regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q82006)