Title: Spectral subsampling MCMC for stationary multivariate time series
Authors: Mattias Villani - Stockholm University (Sweden)
Matias Quiroz - University of Technology Sydney (Australia) [presenting]
Robert Kohn - University of New South Wales (Australia)
Robert Salomone - University of New South Wales (Australia)
Abstract: A subsampling Markov chain Monte Carlo approach is proposed to stationary multivariate time series by subsampling periodogram matrix observations in the frequency domain. We also propose a multivariate generalisation of the autoregressive tempered fractionally differentiated moving average model (ARTFIMA) and establish some of its properties. The new model is shown to provide a better fit compared to multivariate autoregressive moving average models for three real-world examples. We demonstrate that spectral subsampling may provide up to two orders of magnitude faster estimation, while retaining MCMC sampling efficiency and accuracy, compared to spectral methods using the full dataset.