Dynamic functional principal components
From MaRDI portal
Publication:5378118
DOI10.1111/RSSB.12076zbMATH Open1414.62133arXiv1210.7192OpenAlexW2033728423MaRDI QIDQ5378118FDOQ5378118
Authors: Siegfried Hörmann, Łukasz Kidziński, Marc Hallin 
Publication date: 12 June 2019
Published in: Journal of the Royal Statistical Society Series B: Statistical Methodology (Search for Journal in Brave)
Abstract: In this paper, we address the problem of dimension reduction for time series of functional data . Such {it functional time series} frequently arise, e.g., when a continuous-time process is segmented into some smaller natural units, such as days. Then each~ represents one intraday curve. We argue that functional principal component analysis (FPCA), though a key technique in the field and a benchmark for any competitor, does not provide an adequate dimension reduction in a time-series setting. FPCA indeed is a {it static} procedure which ignores the essential information provided by the serial dependence structure of the functional data under study. Therefore, inspired by Brillinger's theory of {it dynamic principal components}, we propose a {it dynamic} version of FPCA, which is based on a frequency-domain approach. By means of a simulation study and an empirical illustration, we show the considerable improvement the dynamic approach entails when compared to the usual static procedure.
Full work available at URL: https://arxiv.org/abs/1210.7192
Recommendations
- Optimal dimension reduction for high-dimensional and functional time series
- Principal components analysis of periodically correlated functional time series
- Principal components for multivariate functional data
- Cramér-Karhunen-Loève representation and harmonic principal component analysis of functional time series
- Principal component analysis for second-order stationary vector time series
principal componentsdimension reductionfunctional data analysisfunctional time seriesfrequency domain analysisKarhunen-Loève expansionfunctional spectral analysis
Nonparametric regression and quantile regression (62G08) Factor analysis and principal components; correspondence analysis (62H25)
Cited In (76)
- Asymptotic normality of spectral means of Hilbert space valued random processes
- Tempered functional time series
- Factor-augmented Model for Functional Data
- An autocovariance-based learning framework for high-dimensional functional time series
- Greedy Segmentation for a Functional Data Sequence
- Functional horseshoe smoothing for functional trend estimation
- A journey from univariate to multivariate functional time series: a comprehensive review
- Nonlinear prediction of functional time series
- A conversation with Marc Hallin
- Quantitative limit theorems and bootstrap approximations for empirical spectral projectors
- A new approach for time domain analysis of multivariate and functional time series
- Factor models for high‐dimensional functional time series I: Representation results
- Variable Selection for the Prediction of C[0,1]-Valued Autoregressive Processes using Reproducing Kernel Hilbert Spaces
- Functional forecasting of dissolved oxygen in high-frequency vertical lake profiles
- Weakly stationary stochastic processes valued in a separable Hilbert space: Gramian-cramér representations and applications
- Dynamic principal component analysis from a global perspective
- Graphical Principal Component Analysis of Multivariate Functional Time Series
- Factor models for high‐dimensional functional time series II: Estimation and forecasting
- Functional singular spectrum analysis
- Trend filtering for functional data
- Principal dynamical components
- Robust functional principal component analysis based on a new regression framework
- Time-varying functional principal components for non-stationary \(\text{EpCO}_2\) in freshwater systems
- Dynamic orthogonal components for multivariate time series
- Functional principal component analysis estimator for non-Gaussian data
- Frequency domain theory for functional time series: variance decomposition and an invariance principle
- Sieve bootstrap for functional time series
- Dynamic principal component analysis with missing values
- White noise testing for functional time series
- High-dimensional functional time series forecasting: an application to age-specific mortality rates
- Functional lagged regression with sparse noisy observations
- An introduction to functional data analysis and a principal component approach for testing the equality of mean curves
- Dynamic principal component regression for forecasting functional time series in a group structure
- Asymptotic properties of principal component projections with repeated eigenvalues
- Testing for periodicity in functional time series
- Rates of convergence of autocorrelation estimates for periodically correlated autoregressive Hilbertian processes
- On consistency and sparsity for high-dimensional functional time series with application to autoregressions
- White noise testing and model diagnostic checking for functional time series
- Sparsely observed functional time series: estimation and prediction
- Extremes of projections of functional time series on data-driven basis systems
- Functional single-index quantile regression models
- A comparison of Hurst exponent estimators in long-range dependent curve time series
- Evaluating trends in time series of distributions: a spatial fingerprint of human effects on climate
- Dynamic principal component regression: application to age-specific mortality forecasting
- A randomness test for functional panels
- Local Whittle estimation of long-range dependence for functional time series
- Inference for the lagged cross-covariance operator between functional time series
- Identifying the finite dimensionality of curve time series
- Dynamic regression models for time-ordered functional data
- Nonparametric estimation of functional dynamic factor model
- freqdom.fda
- Optimal eigen expansions and uniform bounds
- Optimal dimension reduction for high-dimensional and functional time series
- A note on Herglotz's theorem for time series on function spaces
- On seasonal functional modeling under strong dependence, with applications to mechanically ventilated breathing activity
- Pivotal tests for relevant differences in the second order dynamics of functional time series
- Testing for stationarity of functional time series in the frequency domain
- Clustering and forecasting multiple functional time series
- A moment-based notion of time dependence for functional time series
- Cramér-Karhunen-Loève representation and harmonic principal component analysis of functional time series
- Detecting deviations from second-order stationarity in locally stationary functional time series
- Testing equality of spectral density operators for functional processes
- A note on quadratic forms of stationary functional time series under mild conditions
- A bootstrap-based KPSS test for functional time series
- Principal Component Analysis of Spatially Indexed Functions
- An innovations algorithm for the prediction of functional linear processes
- Bootstrap Prediction Bands for Functional Time Series
- Discussion of ``Analysis of spatio-temporal mobile phone data: a case study in the metropolitan area of Milan by P. Secchi, S. Vantini, and V. Vitelli
- A robust functional time series forecasting method
- Rank dynamics for functional data
- On the asymptotic normality of kernel estimators of the long run covariance of functional time series
- On the CLT for discrete Fourier transforms of functional time series
- Feature extraction for functional time series: theory and application to NIR spectroscopy data
- Locally stationary functional time series
- Bootstrap methods for stationary functional time series
- Principal components analysis of periodically correlated functional time series
This page was built for publication: Dynamic functional principal components
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5378118)
