A plug-in bandwidth selection procedure for long-run covariance estimation with stationary functional time series
From MaRDI portal
Publication:5283412
DOI10.1111/JTSA.12229zbMATH Open1367.62094arXiv1604.02724OpenAlexW2964181036WikidataQ58288542 ScholiaQ58288542MaRDI QIDQ5283412FDOQ5283412
Publication date: 21 July 2017
Published in: Journal of Time Series Analysis (Search for Journal in Brave)
Abstract: In arenas of application including environmental science, economics, and medicine, it is increasingly common to consider time series of curves or functions. Many inferential procedures employed in the analysis of such data involve the long run covariance function or operator, which is analogous to the long run covariance matrix familiar to finite dimensional time series analysis and econometrics. This function may be naturally estimated using a smoothed periodogram type estimator evaluated at frequency zero that relies crucially on the choice of a bandwidth parameter. Motivated by a number of prior contributions in the finite dimensional setting, we propose a bandwidth selection method that aims to minimize the estimator's asymptotic mean squared normed error (AMSNE) in . As the AMSNE depends on unknown population quantities including the long run covariance function itself, estimates for these are plugged in in an initial step after which the estimated AMSNE can be minimized to produce an empirical optimal bandwidth. We show that the bandwidth produced in this way is asymptotically consistent with the AMSNE optimal bandwidth, with quantifiable rates, under mild stationarity and moment conditions. These results and the efficacy of the proposed methodology are evaluated by means of a comprehensive simulation study, from which we can offer practical advice on how to select the bandwidth parameter in this setting.
Full work available at URL: https://arxiv.org/abs/1604.02724
Recommendations
- Adaptive bandwidth selection in the long run covariance estimator of functional time series
- Bandwidth selection for functional time series prediction
- Bootstrap-based bandwidth choice for log-periodogram regression
- An algorithm for optimal bandwidth selection for smooth nonparametric quantile estimation
- A two-stage plug-in bandwidth selection and its implementation for covariance estimation
Asymptotic properties of parametric estimators (62F12) Nonparametric estimation (62G05) Asymptotic properties of nonparametric inference (62G20) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10)
Cites Work
- Exact mean integrated squared error
- Nonparametric functional data analysis. Theory and practice.
- Heteroskedasticity and Autocorrelation Consistent Covariance Matrix Estimation
- Linear processes in function spaces. Theory and applications
- Adaptive bandwidth selection in the long run covariance estimator of functional time series
- White noise testing and model diagnostic checking for functional time series
- A functional version of the ARCH model
- Functional Generalized Autoregressive Conditional Heteroskedasticity
- Fourier analysis of stationary time series in function space
- A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix
- PERIODOGRAM ANALYSIS AND CONTINUOUS SPECTRA
- Curve forecasting by functional autoregression
- Weakly dependent functional data
- Evaluating stationarity via change-point alternatives with applications to fMRI data
- On the Prediction of Stationary Functional Time Series
- The impact of bootstrap methods on time series analysis
- HIGHER-ORDER ACCURATE, POSITIVE SEMIDEFINITE ESTIMATION OF LARGE-SAMPLE COVARIANCE AND SPECTRAL DENSITY MATRICES
- An Improved Heteroskedasticity and Autocorrelation Consistent Covariance Matrix Estimator
- Automatic Lag Selection in Covariance Matrix Estimation
- Adaptive bandwidth choice
- Autoregressive forecasting of some functional climatic variations
- Detecting and estimating changes in dependent functional data
- On Consistent Estimates of the Spectrum of a Stationary Time Series
- Testing the structural stability of temporally dependent functional observations and application to climate projections
- Testing stationarity of functional time series
- On the asymptotic normality of kernel estimators of the long run covariance of functional time series
- Multivariate density estimation with general flat-top kernels of infinite order
- A two-stage plug-in bandwidth selection and its implementation for covariance estimation
- On flat-top kernel spectral density estimators for homogeneous random fields
- LOCALLY ADAPTIVE LAG-WINDOW SPECTRAL ESTIMATION
Cited In (25)
- DYNAMIC PRINCIPAL COMPONENT REGRESSION: APPLICATION TO AGE-SPECIFIC MORTALITY FORECASTING
- Long-Range Dependent Curve Time Series
- Tempered functional time series
- Inference for the Lagged Cross‐Covariance Operator Between Functional Time Series
- High-dimensional functional time series forecasting: an application to age-specific mortality rates
- Functional principal component analysis for cointegrated functional time series
- Higher‐Order Accurate Spectral Density Estimation of Functional Time Series
- Dynamic principal component regression for forecasting functional time series in a group structure
- Sparsely observed functional time series: estimation and prediction
- Bandwidth selection for functional time series prediction
- Inference in functional factor models with applications to yield curves
- Moving block and tapered block bootstrap for functional time series with an application to the \(K\)-sample mean problem
- A journey from univariate to multivariate functional time series: a comprehensive review
- A comparison of Hurst exponent estimators in long-range dependent curve time series
- Bootstrapping covariance operators of functional time series
- Testing equality of autocovariance operators for functional time series
- Sieve bootstrapping the memory parameter in long-range dependent stationary functional time series
- How useful is yet another data-driven bandwidth in long-run variance estimation? A simulation study on cointegrating regressions
- Robust change-point detection for functional time series based on \(U\)-statistics and dependent wild bootstrap
- Nonparametric estimation of functional dynamic factor model
- Clustering and forecasting multiple functional time series
- Multiple change point detection in functional data with applications to biomechanical fatigue data
- A robust functional time series forecasting method
- Feature extraction for functional time series: theory and application to NIR spectroscopy data
- Bootstrap methods for stationary functional time series
This page was built for publication: A plug-in bandwidth selection procedure for long-run covariance estimation with stationary functional time series
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5283412)
