Abstract
This chapter is devoted to an approach of extracting periodic or quasi-periodic components from a random signal. Singular Spectrum Analysis (SSA) is not, in a strict sense, a simple spectral method, since it is aimed at representing the signal as a linear combination of elementary variability modes that are not necessarily harmonic components, but can exhibit amplitude and frequency modulations in time, and are data-adaptive, i.e., modeled on the data. It does not provide a stationary spectral estimate but can separate auto-coherent from random features. SSA is a non-parametric method, since it does not assume any specific model for the generation of the signal. It can also be viewed as a powerful de-noising technique; finally, it can be exploited as a tool for filling gaps in data records that is soundly based from a theoretical point of view. Examples the real-world applications of SSA are provided.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Recall that in linear algebra, a Toeplitz matrix is a matrix in which each descending diagonal from left to right is constant, i.e., all elements in a diagonal are equal.
- 2.
We must underline that SVD is different from the so-called eigen-decomposition used to perform diagonalization of a square matrix. Focussing on real matrices, matrix diagonalization is the process of taking a square matrix and converting it into a special type of matrix—a so-called diagonal matrix—that shares the same fundamental properties of the underlying matrix. Matrix diagonalization is equivalent to transforming the underlying system of equations into a special set of coordinate axes in which the matrix takes this diagonal form. Diagonalizing a matrix is also equivalent to finding the matrix’s eigenvalues, which turn out to be precisely the entries of the diagonalized matrix. Similarly, the eigenvectors make up the new set of axes corresponding to the diagonal matrix. The relationship between a diagonalized matrix, eigenvalues, and eigenvectors follows from an equation according to which a square matrix \(\varvec{R}\) can be decomposed into the form \(\varvec{R}= \varvec{A}\varvec{\varLambda }\varvec{A}^{-1}\), where \(\varvec{A}\) is a matrix composed of the eigenvectors of \(\varvec{R}\) arranged by columns, \(\varvec{\varLambda }\) is the diagonal matrix constructed from the corresponding eigenvalues, and \(\varvec{A}^{-1}\) is the matrix inverse of \(\varvec{A}\). It is obvious that if a square matrix \(\varvec{R}\) has a matrix of eigenvectors \(\varvec{A}\) that is not invertible, then \(\varvec{R}\) does not have an eigen-decomposition. However, in the case of the lag-covariance matrix, the eigenvectors are orthogonal to one another. The matrix \(\varvec{A}\) having the eigenvectors of \(\varvec{R}\) as its columns is thus an orthogonal matrix, so that its inverse is equal to its transpose: \(\varvec{A}^{-1}=\varvec{A}^T\). Then \(\varvec{R}\) can be written using a so-called SVD of the form \(\varvec{R}= \varvec{A}\varvec{\varLambda }\varvec{A}^{T}\).
More generally, in linear algebra the SVD is a factorization of a real or complex matrix, which is not necessarily square—it can also be rectangular. Even if linear algebra is beyond the scope of the book, we may mention that some key differences between SVD and eigen-decomposition are the following:
-
the vectors forming the columns of the eigen-decomposition matrix \(\varvec{A}\) are not necessarily orthogonal. On the other hand, the vectors that in the SVD factorization play a similar role are orthonormal; therefore the corresponding matrices—two different matrices—involved in SVD are orthogonal;
-
these matrices involved in SVD are not necessarily the inverse of one another. They are usually not related to each other at all. In the eigen-decomposition, the matrices involved are inverses of each other, i.e., they are \(\varvec{A}\) and \(\varvec{A}^{-1}\);
-
in the SVD, the entries in the diagonal matrix \(\varvec{\varLambda }\) are all real and non-negative. In the eigen-decomposition, the entries of the corresponding matrix can be any complex number—negative, positive, imaginary, whatever;
-
the SVD always exists for any sort of rectangular or square matrix, whereas the eigen-decomposition only exists for square matrices, and even among square matrices sometimes it doesn’t exist.
-
- 3.
The reference standard for the Oxygen isotopic composition in carbonates is the PDB standard, which is based on the CO\({_2}\) produced from Cretaceous belemnites of Pee Dee formation in South Carolina (Faure, G: Principles of isotope geology, Second Edition, John Wiley and Sons (1986)).
- 4.
Siltation, in general, is the pollution of water by fine particulate terrestrial clastic material, with a particle size dominated by silt or clay. Here it refers to the increased accumulation of fine sediments on the river bottom.
- 5.
Swift is a NASA mission with international participation. Within seconds of detecting a burst, Swift relays its location to ground stations, allowing both ground-based and space-based telescopes around the world the opportunity to observe the burst’s afterglow. Swift is part of NASA’s medium explorer (MIDEX) program and was launched into a low-Earth orbit on a Delta 7320 rocket on November 20, 2004.
References
Aguiar-Conraria, L., Soares, M.J.: Business cycle synchronization and the Euro: a wavelet analysis. J. Macroecon. 33, 477–489 (2011)
Alessio, S., Vivaldo, G., Taricco, C., Ghil, M.: Natural variability and anthropogenic effects in a central mediterranean core. Clim. Past 8, 831–839 (2012)
Allen, M.R.: Interactions between the atmosphere and the oceans on time-scales of weeks to years. Ph.D. Dissertation, Clarendon Laboratory, Oxford (1992)
Allen, M.R., Robertson, A.W.: Distinguishing modulated oscillations from coloured noise in multivariate datasets. Clim. Dyn. 12, 775–784 (1996)
Allen, M.R., Smith, L.A.: Monte Carlo SSA: detecting irregular oscillations in the presence of colored noise. J. Climate 9, 3373–3404 (1996)
Allen, M.R., Smith, L.A.: Optimal filtering in singular spectrum analysis. Phys. Lett. A 234(6), 419–428 (1997)
Allen, M.R., Read, P., Smith, L.A.: Temperature oscillations. Nature 359, 679 (1992)
Bonino, G., Cini Castagnoli, G., Callegari, E., Zhu, G.M.: Radiometric and tephroanalysis dating of recent Ionian Sea cores. Nuovo Cimento C 16, 155–161 (1993)
Brawanski, A., Faltermeier, R., Rothoerl, R.D., Woertgen, C.: Comparison of near-infrared spectroscopy and tissue Po\(_2\) time series in patients after severe head injury and aneurysmal subarachnoid hemorrhage. J. Cerebr. Blood F. Met. 22(5), 605–611 (2002)
Broomhead, D.S., King, G.P.: Extracting qualitative dynamics from experimental data. Phys. D 20, 217–236 (1986a)
Broomhead, D.S., King, G.P.: On the qualitative analysis of experimental dynamical systems. In: Sarkar, S. (ed.) Nonlinear Phenomena and Chaos. Adam Hilger, Bristol (1986b)
Colebrook, J.M.: Continuous plankton records, zooplankton and environment, North-East Atlantic and North Sea, 1948–1975. Oceanol. Acta 1, 9–23 (1978)
de Carvalho, M., Rodrigues, P.C., Rua, A.: Tracking the US business cycle with a singular spectrum analysis. Econ. Lett. 114(1), 32–35 (2012)
Dettinger, M.D., Ghil, M., Strong, C.M., Weibel, W., Yiou, P.: Software expedites singular-spectrum analysis of noisy time series. Eos, Trans. American Geophysical Union 76(2), 12, 14, 21 (1995)
De Putter, T., Loutre, M.F., Wansard, G.: Decadal periodicities of Nile River historical discharge (A.D. 622–1470) and climatic implications. Geophys. Res. Lett. 25, 3193–3196 (1998)
Feliks, Y., Groth, A., Robertson, A., Ghil, M.: Oscillatory climate modes in the Indian monsoon, North Atlantic and Tropical Pacific. J. Climate 26, 9528–9544 (2013)
Freas, W.A., Sieurin, E.: A nonparametric calibration procedure for multi-source urban air pollution dispersion models. In: Fifth Conference on Probability and Statistics in Atmospheric Sciences. American Meteorological Society (AMS), Las Vegas (1977)
Ghaleb, K.O.: Le Mikyas ou Nilomètre de l’\(\hat{\rm {l}}\)le de Rodah. Mem. Inst. Egypte, 54 (1951)
Ghil, M., Taricco, C.: Advanced spectral analysis methods. In: Cini Castagnoli, G. Provenzale, A. (eds.) Past and Present Variability of the Solar-Terrestrial System: Measurement, Data Analysis and Theoretical Models. Società Italiana di Fisica, Bologna, Italy & IOS Press, Amsterdam (1997)
Ghil, M., Allen, M.R., Dettinger, M.D., Ide, K., Kondrashov, D., Mann, M.E., Robertson, A.W., Saunders, A., Tian, Y., Varadi, F., Yiou, P.: Advanced spectral methods for climatic time series. Rev. Geophys. 40(1), 1.1–1.41 (2002)
Golyandina, N., Nekrutkin, V., Zhigliavsky, A.: Analysis of Time Series Structure: SSA and Related Techniques. Chapman & Hall/CRC, Boca Raton (2001)
Golyandina, N., Stepanov, D.: SSA-Based approaches to analysis and forecast of multidimensional time series. In: Proceedings of the 5th St. Petersburg Workshop on Simulation, June 26-July 2, 2005, pp. 293-298. St. Petersburg State University, St. Petersburg (2005)
Golyandina, N., Zhigljavsky, A.: Singular Spectrum Analysis for Time Series. Springer, Berlin (2013)
Greco, G., Rosa, R., Beskin, G., Karpov, S., Romano, L., Guarnieri, A., Bartolini, C., Bedogni, R.: Evidence of deterministic components in the apparent randomness of GRBs: clues of a chaotic dynamic. Sci. Rep. 1, 91 (2011)
Grigorov, M.: Global dynamics of biological systems from time-resolved omics experiments. Bioinformatics 22(12), 1424–1430 (2006)
Groth, A., Ghil, M.: Multivariate singular spectrum analysis and the road to phase synchronization. Phys. Rev. E 84(036206), 1–10 (2011)
Groth, A., Ghil, M., Hallegatte, S., Dumas, P.: The Role of Oscillatory Modes in U.S. Business Cycles. Working Paper 26. Fondazione ENI Enrico Mattei (FEEM), Milan (2012)
Hallegatte, S., Ghil, M., Dumas, P., Hourcade, J.: Business cycles, bifurcations and chaos in neo-classical model with investment dynamics. J. Econ. Behav. Organ. 67, 57–77 (2008)
Hassani, H., Thomakos, D.: A review on singular spectrum analysis for economic and financial time series. Stat. Interf. 3(3), 377–397 (2010)
Hassani, H., Soofi, A., Zhigljavsky, A.: Predicting daily exchange rate with singular spectrum analysis. Nonlinear Anal.: Real World Appl. 11, 2023–2034 (2011)
Hassani, H., Heravi, S., Zhigljavsky, A.: Forecasting UK industrial production with multivariate singular spectrum analysis. J. Forecast. 32(5), 395–408 (2013)
Hassani, H., Mahmoudvand, R.: Multivariate singular spectrum analysis: a general view and new vector forecasting approach. Int. J. Energy Stat. 1(1), 55–83 (2013)
Hayes, M.H.: Statistical Digital Signal Processing and Modeling. Wiley, New York (1996)
Hirsch, R.M., Slack, J.R.: A nonparametric trend test for seasonal data with serial dependence. Water Resour. Res. 20(6), 727–732 (1984)
Hirsch, R.M., Slack, J.R., Smith, R.A.: Techniques of trend analysis for monthly water quality data. Water Resour. Res. 18(1), 107–121 (1982)
Hodrick, R., Prescott, E.C.: Postwar U.S. business cycles: an empirical investigation. J. Money, Credit, Banking 29(1), 1–16 (1997)
Kaiser, H.F.: The varimax criterion for analytic rotation in factor analysis. Psychometrika 23(3), 187–200 (1958)
Hurst, H.E.: The Nile. Constable, London (1952)
Karhunen, K.: Zur Spektraltheorie stochastischer prozesse. Annales Academiae Scientiarum Fennicae, Ser. A1, Math.-Phys., 34, 1–7 (1946)
Karhunen, K.: ber lineare Methoden in der Wahrscheinlichkeitsrechnung. Annales Academiae Scientiarum Fennicae, Ser. A1, Math.-Phys., 37, 1–79 (1947)
Keppenne, C.L., Ghil, M.: Adaptive filtering and prediction of the Southern Oscillation index. J. Geophys. Res. 97, 20449–20454 (1992)
Keppenne, C.L., Ghil, M.: Adaptive filtering and prediction of noisy multivariate signals: an application to subannual variability in atmospheric angular momentum. Intl. J. Bifurcat. Chaos 3, 625–634 (1993)
Kondrashov, D., Ghil, M.: Spatio-temporal filling of missing points in geophysical data sets. Nonlin. Process. Geophys. 13, 151–159 (2006)
Kondrashov, D., Feliks, Y., Ghil, M.: Oscillatory modes of extended Nile River records (A.D. 622–1922). Geophys. Res. Lett. 32, L10702 (2005)
Kondrashov, D., Shprits, Y.Y., Ghil, M.: Gap filling of solar wind data by singular spectrum analysis. Geophys. Res. Lett. 37, L15101 (2010)
Kondrashov, D., Denton, R., Shprits, Y.Y., Singer, H.J.: Reconstruction of gaps in the past history of solar wind parameters. Geophys. Res. Lett. 41, 2702–2707 (2014)
Loéve, M.: Probability Theory, Vol. II. Graduate Texts in Mathematics, vol. 46. Springer, Berlin (1978)
Mac Lane, S., Birkhoff, G.: Algebra. AMS Chelsea Publishing, New York (1999)
Mañé, R.: On the Dimension of the Compact Invariant Sets of Certain Non-Linear Maps. Dynamical Systems and Turbulence. Lecture Notes in Mathematics, vol. 898, pp. 230–242. Springer, Berlin (1981)
Mann, M.E., Lees, J.M.: Robust estimation of background noise and signal detection in climatic time series. Clim. Change 33(3), 409–445 (1996)
Mineva, A., Popivanov, D.: Method of single-trial readiness potential identification, based on singular spectrum analysis. J. Neurosci. Methods 68, 91–99 (1996)
Patterson, K., Hassani, H., Heravi, S., Zhigljavsky, A.: Multivariate singular spectrum analysis for forecasting revisions to real-time data. J. Appl. Stat. 38(10), 2183–2211 (2011)
Penland, C., Ghil, M., Weickmann, K.M.: Adaptive filtering and maximum entropy spectra, with application to changes in atmospheric angular momentum. J. Geophys. Res. 96, 22659–22671 (1991)
Plaut, G., Vautard, R.: Spells of low-frequency oscillations and weather regimes in the northern hemisphere. J. Atmos. Sci. 51(2), 210–236 (1994)
Popper, W.: The Cairo Nilometer. University of California Press, Berkeley (1951)
Quinn, W.H.: A Study of Southern Oscillation-Related Climatic Activity for A.D. 622–1900 Incorporating Nile River Flood Data. In: Diaz, H.F., Markgraf, V. (eds.) El Niño: Historical and Paleoclimatic Aspects of the Southern Oscillation. Cambridge University Press, New York (1992)
Robertson, A.W., Mechoso, C.R.: Interannual and interdecadal variability of the South Atlantic convergence zone. Mon. Wea. Rev. 128, 2947–2957 (2000)
Rodó, X., Pascual, M., Fuchs, G., Faruque, A.S.G.: ENSO and cholera: a nonstationary link related to climate change? Proc. Nat. Acad. Sci. USA 99(20), 12901–12906 (2002)
Sella, L.: Old and New Spectral Techniques for Economic Time Series. Cognetti de Martiis Working Papers Series, N. 09/2008. Department of Economics. Torino University, Torino (2008)
Sella, L., Marchionatti, R.: On the cyclical variability of economic growth in Italy, 1881–1913: a critical note. Cliometrica 6(3), 307–328 (2012)
Sella, L., Vivaldo, G., Groth, A., Ghil, M.: Economic Cycles and Their Synchronization: A Survey of Spectral Properties. Working Paper 105.2013. Fondazione ENI Enrico Mattei (FEEM), Milan (2013)
Shackleton, N.J., Kennett, J.P.: Palaeo-temperature history of the cenozoic and the initiation of Antarctic Glaciation: oxygen and carbon isotope analysis in DSDP Sites 277, 279 and 281. In: Kennett, J.P., Houtz, R.E. (eds.) Initial Reports of the Deep Sea Drilling Project, vol. 5, pp. 743–755. US Government Printing Office, Washington (1975)
Takens, F.: Detecting Strange Attractors in Turbulence. Dynamical Systems and Turbulence. Lecture Notes in Mathematics, vol. 898, pp. 366–381. Springer, Berlin (1981)
Taricco, C., Ghil, M., Alessio, S., Vivaldo, G.: Two millennia of climate variability in the central mediterranean. Clim. Past 5, 171–181 (2009)
Taricco, C., Vivaldo, G., Alessio, S., Rubinetti, S., Mancuso, S.: A high-resolution \(\delta ^{18}\)O record and Mediterranean climate variability. Clim. Past 11, 509–522 (2015)
Thomakos, D.D., Tao Wang, T., Wille, L.T.: Modeling daily realized futures volatility with singular spectrum analysis. Phys. A, Stat. Mech. Appl. 312(3–4), 505–519 (2002)
Toussoun, O.: Mémoire sur l’histoire du Nil. Mem. Inst. Egypte 18, 366–404 (1925)
Vautard, R., Ghil, M.: Singular spectrum analysis in nonlinear dynamics, with applications to paleoclimatic time series. Phys. D 35, 395–424 (1989)
Vautard, R., Yiou, P., Ghil, M.: Singular-spectrum analysis: a toolkit for short, noisy. Chaotic Signals. Phys. D 58, 95–126 (1992)
Walker, G.T.: Correlation in seasonal variations of weather: II. Indian Meteorol. Mem. 21, 1–21 (1910)
Whitcher, B.J., Byers, S.D., Guttorp, P., Percival, D.B.: Testing for homogeneity of variance in time series: long memory, wavelets and the Nile River. Water Resour. Res. 38(5), 12-1–12-16 (2002)
Whittaker, E.T.: On a new method of graduation. Proc. Edinburgh Math. Assoc. 41, 63–75 (1923)
Zhigljavsky, A. (Ed.): Special issue on theory and practice in singular spectrum analysis of time series. Stat. Interf. 3(3) (2010)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Alessio, S.M. (2016). Singular Spectrum Analysis (SSA). In: Digital Signal Processing and Spectral Analysis for Scientists. Signals and Communication Technology. Springer, Cham. https://doi.org/10.1007/978-3-319-25468-5_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-25468-5_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25466-1
Online ISBN: 978-3-319-25468-5
eBook Packages: EngineeringEngineering (R0)