Sliced average variance estimation for multivariate time series

ABSTRACT Supervised dimension reduction for time series is challenging as there may be temporal dependence between the response y and the predictors . Recently a time series version of sliced inverse regression, TSIR, was suggested, which applies approximate joint diagonalization of several supervised lagged covariance matrices to consider the temporal nature of the data. In this paper, we develop this concept further and propose a time series version of sliced average variance estimation, TSAVE. As both TSIR and TSAVE have their own advantages and disadvantages, we consider furthermore a hybrid version of TSIR and TSAVE. Based on examples and simulations we demonstrate and evaluate the differences between the three methods and show also that they are superior to apply their iid counterparts to when also using lagged values of the explaining variables as predictors.

• Publication year

  2018

• Venue

  Statistics (Berlin)

• Publication date

  2018-10-05

• Fields of study

  Mathematics

• Identifiers
  DOI 10.1080/02331888.2019.1605515arXiv 1810.02782
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Asymptotic and Bootstrap Tests for the Dimension of the Non-Gaussian Subspace

  2017cited by this paper
• A Unified Framework for Dimension Reduction in Forecasting

  2017cited by this paper
• Blind Source Separation Based on Joint Diagonalization in R: The Packages JADE and BSSasymp

  2017cited by this paper
• Supervised dimension reduction for multivariate time series

  2017influential reference
• Combining eigenvalues and variation of eigenvectors for order determination

  2016cited by this paper
• An Empirical Process View of Inverse Regression

  2016cited by this paper
• Forecasting with Sufficient Dimension Reductions

  2015cited by this paper
• New independent component analysis tools for time series

  2015cited by this paper
• Model selection using limiting distributions of second-order blind source separation algorithms

  2015cited by this paper
• Fourth Moments and Independent Component Analysis

  2014influential reference
• Joint Matrices Decompositions and Blind Source Separation: A survey of methods, identification, and applications

  2014cited by this paper
• Deflation-based separation of uncorrelated stationary time series

  2014cited by this paper
• Supervised invariant coordinate selection

  2014cited by this paper
• Separation of Uncorrelated Stationary time series using Autocovariance Matrices

  2014cited by this paper
• A Review on Dimension Reduction

  2013cited by this paper
• Time series factor models

  2013cited by this paper
• Iterative application of dimension reduction methods

  2011influential reference
• Communications in Statistics-Simulation and Computation

  2008cited by this paper
• Asymptotics for sliced average variance estimation

  2007influential reference
• On hybrid methods of inverse regression-based algorithms

  2007influential reference
• On the use of joint diagonalization in blind signal processing

  2006cited by this paper
• Sufficient Dimension Reduction via Inverse Regression

  2005cited by this paper
• Sliced Inverse Regression for High-dimensional Time Series

  2003influential reference
• Using the Bootstrap to Select One of a New Class of Dimension Reduction Methods

  2003cited by this paper
• AN ASYMPTOTIC THEORY FOR SIRα METHOD

  2003cited by this paper
• An adaptive estimation of dimension reduction space

  2002influential reference
• POOLED SLICING METHODS VERSUS SLICING METHODS

  2001cited by this paper
• Estimating the structural dimension of regressions via parametric inverse regression

  2001influential reference
• Identifying Regression Outliers and Mixtures Graphically

  2000influential reference
• Save: a method for dimension reduction and graphics in regression

  2000cited by this paper
• BOARD OF GOVERNORS OF THE FEDERAL RESERVE SYSTEM

  1997cited by this paper
• Jacobi Angles for Simultaneous Diagonalization

  1996cited by this paper
• Asymptotics of sliced inverse regression

  1995cited by this paper
• Comments on "Sliced inverse regression for dimension reduction" by K. C. Li

  1991cited by this paper
• Sliced Inverse Regression for Dimension Reduction

  1991influential reference
• Sliced Inverse Regression for Dimension Reduction - Comment

  1991influential reference

• Forecasting High Dimensional Time Series with Dynamic Dimension Reduction

  2025cites this paper
• Slicing-free supervised dimension reduction for multivariate time series

  2025influential citation
• Fourier methods for efficient sufficient dimension reduction in time series

  2025cites this paper
• Using sliced inverse mean difference for dimension reduction in multivariate time series

  2024cites this paper
• Blind recovery of sources for multivariate space-time random fields

  2022cites this paper
• Advances in blind source separation for spatial data

  2021cites this paper
• Stationary subspace analysis based on second-order statistics

  2021cites this paper
• Dimension Reduction for Time Series in a Blind Source Separation Context Using R

  2021influential citation
• On the usage of joint diagonalization in multivariate statistics

  2021cites this paper
• Sliced Inverse Regression for Spatial Data

  2020cites this paper
• On Independent Component Analysis and Supervised Dimension Reduction for Time Series

  2018cites this paper