On the optimal reconstruction of partially observed functional data

DOI10.1214/19-AOS1864MaRDI QIDQ2196241zbMATH OpenFDO

Authors Alois Kneip, Dominik Liebl

Publication date 28 August 2020

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1710.10099, https://projecteuclid.org/euclid.aos/1594972835

zbMATH Keywords

functional data analysisfunctional principal componentsincomplete functions

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Nonparametric regression and quantile regression (62G08) Factor analysis and principal components; correspondence analysis (62H25) Inference from stochastic processes and prediction (62M20) Functional data analysis (62R10)

Abstract: We propose a new reconstruction operator that aims to recover the missing parts of a function given the observed parts. This new operator belongs to a new, very large class of functional operators which includes the classical regression operators as a special case. We show the optimality of our reconstruction operator and demonstrate that the usually considered regression operators generally cannot be optimal reconstruction operators. Our estimation theory allows for autocorrelated functional data and considers the practically relevant situation in which each of the $n$ functions is observed at $m_i$, $i=1,dots,n$, discretization points. We derive rates of consistency for our nonparametric estimation procedures using a double asymptotic. For data situations, as in our real data application where $m_i$ is considerably smaller than $n$, we show that our functional principal components based estimator can provide better rates of convergence than conventional nonparametric smoothing methods.

Recommendations

• Ridge reconstruction of partially observed functional data is asymptotically optimal
• Partially observed functional data
• Components and Completion of Partially Observed Functional Data
• Inferential procedures for partially observed functional data
• Functional regression with dependent error and missing observation in reproducing kernel Hilbert spaces

Cites work

• scientific article; zbMATH DE number 469335 (Why is no real title available?)
• Approximating fragmented functional data by segments of Markov chains
• CLT in functional linear regression models
• Classification using censored functional data
• Components and Completion of Partially Observed Functional Data
• From sparse to dense functional data and beyond
• Functional Data Analysis for Sparse Longitudinal Data
• Functional data analysis.
• Functional linear regression analysis for longitudinal data
• Inference for functional data with applications
• Linear processes in function spaces. Theory and applications
• Methodology and convergence rates for functional linear regression
• Modeling and forecasting electricity spot prices: a functional data perspective
• Nonparametric testing for differences in electricity prices: the case of the Fukushima nuclear accident
• Predicting the continuation of a function with applications to call center data
• Prediction in functional linear regression
• Properties of principal component methods for functional and longitudinal data analysis
• Recovering covariance from functional fragments
• Statistical inferences for functional data
• Uniform convergence rates for nonparametric regression and principal component analysis in functional/longitudinal data

Cited in

(30)

• Comments on: ``Exploratory functional data analysis
• Functional nonlinear principal component analysis
• The completion of covariance kernels
• Inferential procedures for partially observed functional data
• On functional logistic regression: some conceptual issues
• Testing linear operator constraints in functional response regression with incomplete response functions
• Partially observed functional data: the case of systematically missing parts
• Covariate-informed reconstruction of partially observed functional data via factor models
• Partially observed functional data
• Recovering gradients from sparsely observed functional data
• Mean and Covariance Estimation for Functional Snippets
• Multiple imputation in the functional linear model with partially observed covariate and missing values in the response
• A Bayesian multiple imputation approach to bivariate functional data with missing components
• Regionalization of China's PM₂.5: a robust functional spatial clustering with angular depth
• Depth-based reconstruction method for incomplete functional data
• Weighted Functional Data Analysis for the Calibration of a Ground Motion Model in Italy
• A new algorithm for the imputation of missing functional data
• On the functional regression model and its finite-dimensional approximations
• Robust Inference for Partially Observed Functional Response Data
• Integrated Depths for Partially Observed Functional Data
• Scalar-on-function regression with partially observed covariate
• Regularized nonparametric estimation of covariance kernels for high-dimensional interferometric data
• The functional graphical lasso
• Supervised Manifold Learning for Functional Data
• Localization processes for functional data analysis
• Dynamic modelling of sparse longitudinal data and functional snippets with stochastic differential equations
• Ridge reconstruction of partially observed functional data is asymptotically optimal
• Components and Completion of Partially Observed Functional Data
• Functional linear model with partially observed covariate and missing values in the response
• Partial linear quantile regression model with incompletely observed functional covariates

Describes a project that uses

Uses Software

• fda (R)

This page was built for publication: On the optimal reconstruction of partially observed functional data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2196241)