Spectral Analysis of Multivariate Time Series
(2019) , 24 pages
Files
ISBADP2019_08_vonsachst_SpectralAnalysisofMultivariateTimeSeries_dial.pdf
Open Access - Adobe PDF
- 4.28 MB
Details
- Authors
- Abstract
- Spectral Analysis of Multivariate Time Series has been an active field of methodological and applied statistics for the past 50 years. Since the success of the Fast Fourier Transform algorithm, the analysis of serial auto- and cross correlation in the frequency domain has helped a lot in understanding the dynamics in many serially correlated data without necessarily needing to develop complex parametric models. In this work, we will give a non-exhaustive review on, mostly recent, nonparametric methods of spectral analysis of multivariate time series, with a certain emphasis on model-based approaches. We try to give insights into a variety of complimentary approaches, for standard and less standard situations (such a non-stationary, replicated or high-dimensional time series), discuss estimation aspects (such as smoothing over frequency) and include some examples stemming from life science applications (brain data).
- Affiliations
Citations
von Sachs, R. (2019). Spectral Analysis of Multivariate Time Series (ISBA Discussion Paper 2019/08). https://hdl.handle.net/2078.5/123721