Forecasting multiple time series with one-sided dynamic principal components
From MaRDI portal
Publication:5208073
DOI10.1080/01621459.2018.1520117zbMATH Open1428.62401arXiv1708.04705OpenAlexW2963724581MaRDI QIDQ5208073FDOQ5208073
Authors: Daniel Peña, Ezequiel Smucler, Victor J. Yohai 
Publication date: 15 January 2020
Published in: Journal of the American Statistical Association (Search for Journal in Brave)
Abstract: We define one-sided dynamic principal components (ODPC) for time series as linear combinations of the present and past values of the series that minimize the reconstruction mean squared error. Previous definitions of dynamic principal components depend on past and future values of the series. For this reason, they are not appropriate for forecasting purposes. On the contrary, it is shown that the ODPC introduced in this paper can be successfully used for forecasting high-dimensional multiple time series. An alternating least squares algorithm to compute the proposed ODPC is presented. We prove that for stationary and ergodic time series the estimated values converge to their population analogues. We also prove that asymptotically, when both the number of series and the sample size go to infinity, if the data follows a dynamic factor model, the reconstruction obtained with ODPC converges, in mean squared error, to the common part of the factor model. Monte Carlo results shows that forecasts obtained by the ODPC compare favourably with other forecasting methods based on dynamic factor models.
Full work available at URL: https://arxiv.org/abs/1708.04705
Recommendations
- scientific article; zbMATH DE number 1489820
- The Generalized Dynamic Factor Model
- Forecasting Using Principal Components From a Large Number of Predictors
- The generalized dynamic factor model: one-sided estimation and forecasting
- Principal component analysis for second-order stationary vector time series
Factor analysis and principal components; correspondence analysis (62H25) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10)
Cites Work
- Forecasting Using Principal Components From a Large Number of Predictors
- Title not available (Why is that?)
- Statistics for high-dimensional data. Methods, theory and applications.
- OPENING THE BLACK BOX: STRUCTURAL FACTOR MODELS WITH LARGE CROSS SECTIONS
- Determining the Number of Factors in Approximate Factor Models
- The Generalized Dynamic Factor Model
- Dynamic factor models with infinite-dimensional factor spaces: one-sided representations
- Determining the Number of Factors in the General Dynamic Factor Model
- Large Covariance Estimation by Thresholding Principal Orthogonal Complements
- Title not available (Why is that?)
- Identifying a Simplifying Structure in Time Series
- A canonical analysis of multiple time series
- High breakdown-point and high efficiency robust estimates for regression
- Title not available (Why is that?)
- Coordinate descent algorithms
- Nested Reduced-Rank Autogressive Models for Multiple Time Series
- Robust and sparse estimators for linear regression models
- Forecasting with nonstationary dynamic factor models
- Dynamic factor models with infinite-dimensional factor space: asymptotic analysis
- Factor models in high-dimensional time series: A time-domain approach
- Title not available (Why is that?)
- Title not available (Why is that?)
Cited In (7)
- Data science, big data and statistics
- Robust forecasting of multiple time series with one-sided dynamic principal components
- Title not available (Why is that?)
- Extracting a low-dimensional predictable time series
- Testing Serial Correlation and ARCH Effect of High-Dimensional Time-Series Data
- Forecasting time series using principal component analysis with respect to instrumental variables
- Consistency of generalized dynamic principal components in dynamic factor models
Uses Software
This page was built for publication: Forecasting multiple time series with one-sided dynamic principal components
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5208073)
