Weakly dependent functional data

Abstract

Functional data often arise from measurements on fine time grids and are obtained by separating an almost continuous time record into natural consecutive intervals, for example, days. The functions thus obtained form a functional time series, and the central issue in the analysis of such data consists in taking into account the temporal dependence of these functional observations. Examples include daily curves of financial transaction data and daily patterns of geophysical and environmental data. For scalar and vector valued stochastic processes, a large number of dependence notions have been proposed, mostly involving mixing type distances between $\sigma$-algebras. In time series analysis, measures of dependence based on moments have proven most useful (autocovariances and cumulants). We introduce a moment-based notion of dependence for functional time series which involves $m$-dependence. We show that it is applicable to linear as well as nonlinear functional time series. Then we investigate the impact of dependence thus quantified on several important statistical procedures for functional data. We study the estimation of the functional principal components, the long-run covariance matrix, change point detection and the functional linear model. We explain when temporal dependence affects the results obtained for i.i.d. functional observations and when these results are robust to weak dependence.

Published in at http://dx.doi.org/10.1214/09-AOS768 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
• Break detection in the covariance structure of multivariate time series models
• Common functional principal components
• Augmented GARCH sequences: Dependence structure and asymptotics

Cited by in corpus (60)

• Uniform change point tests in high dimension
• Estimation in functional linear quantile regression
• Fourier analysis of stationary time series in function space
• Evaluating stationarity via change-point alternatives with applications to fMRI data
• Prediction of functional ARMA processes with an application to traffic data
• Locally Stationary Functional Time Series
• An Innovations Algorithm for the prediction of functional linear processes
• Recent Developments in Complex and Spatially Correlated Functional Data
• Testing for stationarity of functional time series in the frequency domain
• Two sample inference for the second-order property of temporally dependent functional data
• Consistency of the mean and the principal components of spatially distributed functional data
• Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence
• Unified Principal Component Analysis for Sparse and Dense Functional Data under Spatial Dependency
• A nonparametric test for stationarity in functional time series
• An autocovariance-based learning framework for high-dimensional functional time series
• Functional time series prediction under partial observation of the future curve
• Conformal Prediction Bands for Two-Dimensional Functional Time Series
• Sparsely Observed Functional Time Series: Estimation and Prediction
• Break Point Detection for Functional Covariance
• Graphical Principal Component Analysis of Multivariate Functional Time Series
• A change-point detection method for detecting and locating the abrupt changes in distributions of damage-sensitive features of SHM data, with application to structural condition assessment
• A note on quadratic forms of stationary functional time series under mild conditions
• Elastic Functional Changepoint Detection of Climate Impacts from Localized Sources
• Detection of periodicity in functional time series
• Functional Lagged Regression with Sparse Noisy Observations
• Factor modelling for high-dimensional functional time series
• Finite Sample Theory for High-Dimensional Functional/Scalar Time Series with Applications
• Topological reconstruction of compact supports of dependent stationary random variables
• Consistently recovering the signal from noisy functional data
• Parameter Regimes in Partial Functional Panel Regression
• Functional Autoregressive Processes in Reproducing Kernel Hilbert Spaces
• Kernel Autocovariance Operators of Stationary Processes: Estimation and Convergence
• Statistical Depth Meets Machine Learning: Kernel Mean Embeddings and Depth in Functional Data Analysis
• On the estimation of locally stationary functional time series
• Spectral Simulation of Functional Time Series
• Statistical Inference for High Dimensional Panel Functional Time Series
• Testing normality of spatially indexed functional data
• A note on estimation in Hilbertian linear models
• Principal component analysis of periodically correlated functional time series
• Test of Weak Separability for Spatially Stationary Functional Field
• Spectral analysis of long range dependence functional time series
• Predicting seasonal influenza transmission using Regression Models with Temporal Dependence
• Variation Pattern Classification of Functional Data
• A functional approach to deconvolve dynamic neuroimaging data
• Filtrated Common Functional Principal Components for Multivariate Functional data
• An information criterion for detecting periodicities in functional time series
• Forecasting high-dimensional functional time series with dual-factor structures
• Feature Extraction for Functional Time Series: Theory and Application to NIR Spectroscopy Data
• Factor-augmented Smoothing Model for Functional Data
• Factor Models for High-Dimensional Functional Time Series
• Higher-order Accurate Spectral Density Estimation of Functional Time Series
• The autoregression bootstrap for kernel estimates of smooth nonlinear functional time series
• Yield curve and macroeconomy interaction: evidence from the non-parametric functional lagged regression approach
• Sequential Monitoring of Changes in Housing Prices
• Rate of convergence for Hilbert space valued processes
• Detecting and dating structural breaks in functional data without dimension reduction
• Bootstrap for dependent Hilbert space-valued random variables with application to von Mises statistics
• Testing for independence between functional time series
• Convergence of Nonparametric Functional Regression Estimates with Functional Responses
• Detecting changes in functional linear models