Nonstationary data analysis by time deformation. (English) Zbl 1062.62211

Gray, Henry L.; Vijverberg, Chu-Ping C.; Woodward, Wayne A.

Commun. Stat., Theory Methods 34, No. 1, 163-192 (2005).

Summary: We discuss methodology for analyzing nonstationary time series whose periodic nature changes approximately linearly with time. We make use of the M-stationary process to describe such data sets, and in particular we use the discrete Euler(\(p\)) model to obtain forecasts and estimate the spectral characteristics. We discuss the use of the M-spectrum for displaying linear time-varying periodic contents in a time series realization in much the same way that the spectrum shows periodic content within a realization of a stationary series. We also introduce the instantaneous frequency and spectrum of an M-stationary process for purposes of describing how frequency changes with time.
To illustrate our techniques we use one simulated data set and two bat echolocation signals that show time varying frequency behavior. Our results indicate that for data whose periodic content is changing approximately linearly in time, the Euler model serves as a very good model for spectral analysis, filtering, and forecasting. Additionally, the instantaneous spectrum is shown to provide better representation of the time-varying frequency content in the data than window-based techniques such as the Gabor and wavelet transforms. Finally, it is noted that the results of this article can be extended to processes whose frequencies change like \(at^{\alpha}\), \(a > 0\), \(-\infty < \alpha <-\infty\).

MSC:

62M15	Inference from stochastic processes and spectral analysis
62M10	Time series, auto-correlation, regression, etc. in statistics (GARCH)
62P35	Applications of statistics to physics
62P10	Applications of statistics to biology and medical sciences; meta analysis

Keywords:

Euler processes; M-stationary processes; nonstationary; time deformation

References:

[1]	Box G. E. P., 3rd ed., in: Time Series Analysis: Forecasting and Control (1994) · Zbl 0858.62072
[2]	Girardin V., Computers and Mathematics with Application 6 pp 1009– (2003) · Zbl 1045.62093
[3]	DOI: 10.3150/bj/1066418881 · Zbl 1043.60026
[4]	DOI: 10.1111/j.1467-9892.1988.tb00460.x · Zbl 0642.60024
[5]	Gray , H. L. , Vijverberg , C. P. ( 2003 ). Time deformation and the M-spectrum—a new tool for cyclical analysis. Southern Methodist University Department of Statistical Science Technical Report SMU-TR-314.
[6]	Herr A., Complexity International pp 4– (1997)
[7]	Jiang , H. , Gray , H. L. , Woodward , W. A. ( 2003 ). Time varying frequency analysis–G({\(\lambda\)}) stationary processes. Southern Methodist University Department of Statistical Science Technical Report SMU-TR-311. · Zbl 1157.62501
[8]	Liu , L. , Gray , H. L. , Woodward , W. A. ( 2004 ). On the analysis of linear and quadratic chirp processes using time deformation. Southern Methodist University Department of Statistical Science Technical Report SMU-TR-317.
[9]	Vijverberg , C.P. C. ( 2002 ). Discrete multiplicative stationary processes. Ph.D. Dissertation, Department of Statistical Science, Southern Methodist University.
[10]	Vijverberg , C. P. , Gray , H. L. ( 2003 ). Time deformation and the M-spectrum—a new tool for cyclical analysis. Southern Methodist University Department of Statistical Science Technical Report SMU-TR-314.
[11]	DOI: 10.1109/10.871405