A frequency domain bootstrap for general multivariate stationary processes

Abstract: For many relevant statistics of multivariate time series, no valid frequency domain bootstrap procedures exist. This is mainly due to the fact that the distribution of such statistics depends on the fourth-order moment structure of the underlying process in nearly every scenario, except for some special cases like Gaussian time series. In contrast to the univariate case, even additional structural assumptions such as linearity of the multivariate process or a standardization of the statistic of interest do not solve the problem. This paper focuses on integrated periodogram statistics as well as functions thereof and presents a new frequency domain bootstrap procedure for multivariate time series, the multivariate frequency domain hybrid bootstrap (MFHB), to fill this gap. Asymptotic validity of the MFHB procedure is established for general classes of periodogram-based statistics and for stationary multivariate processes satisfying rather weak dependence conditions. A simulation study is carried out which compares the finite sample performance of the MFHB with that of the moving block bootstrap.

[1]  Marco Meyer,et al.  On the Vector Autoregressive Sieve Bootstrap , 2015 .

[2]  David Hinkley,et al.  Bootstrap Methods: Another Look at the Jackknife , 2008 .

[3]  M. Rosenblatt.  Stationary sequences and random fields , 1985 .

[4]  Eric R. Ziegel,et al.  Time Series: Theory and Methods (2nd ed,) , 2012 .

[5]  Christian Francq,et al.  Estimating multivariate volatility models equation by equation , 2016 .

[6]  Extending the validity of frequency domain bootstrap methods to general stationary processes , 2020 .

[7]  B. A. Schmitt.  Perturbation bounds for matrix square roots and pythagorean sums , 1992 .

[8]  W. Wu,et al.  ASYMPTOTIC THEORY FOR SPECTRAL DENSITY ESTIMATES OF GENERAL MULTIVARIATE TIME SERIES , 2018, Econometric Theory.

[9]  Jens-Peter Kreiss,et al.  The multiple hybrid bootstrap - Resampling multivariate linear processes , 2010, J. Multivar. Anal..

[10]  Saralees Nadarajah,et al.  Moments and cumulants for the complex Wishart , 2012, J. Multivar. Anal..

[11]  細谷 雄三.  書評 Asymptotic Theory of Statistical Inference for Time Series (Springer Series in statistics), (2000) Springer, Masanobu Taniguchi and Yoshihide Kakizawa , 2001 .

[12]  P. Robinson,et al.  AUTOMATIC FREQUENCY DOMAIN INFERENCE ON SEMIPARAMETRIC AND NONPARAMETRIC MODELS , 1991 .

[13]  Wolfgang Härdle,et al.  On Bootstrapping Kernel Spectral Estimates , 1992 .

[14]  Efstathios Paparoditis,et al.  Extending the Range of Validity of the Autoregressive (Sieve) Bootstrap , 2018 .

[15]  R. Dahlhaus.  On a spectral density estimate obtained by averaging periodograms , 1985, Journal of Applied Probability.

[16]  D. Politis,et al.  On the range of validity of the autoregressive sieve bootstrap , 2012, 1201.6211.

[17]  D. B. Preston.  Spectral Analysis and Time Series , 1983 .

[18]  E. Paparoditis,et al.  The Hybrid Wild Bootstrap for Time Series , 2012 .

[19]  R. Dahlhaus,et al.  A frequency domain bootstrap for ratio statistics in time series analysis , 1996 .

[20]  D. Politis,et al.  Convolved subsampling estimation with applications to block bootstrap , 2017, The Annals of Statistics.

[21]  Harald E. Krogstad.  ON THE COVARIANCE OF THE PERIODOGRAM , 1982 .