Abstract
This paper considers the problem of smoothing a non-stationary time series (having either deterministic and/or stochastic trends) using the discrete cosine transform (DCT). The DCT is a powerful tool which has found fruitful applications in filtering and smoothing as it can closely approximate the optimal Karhunen-Loeve transform (KLT). In fact, it is known that it almost corresponds to the KLT for first-order autoregressive processes with a root close to unity: This is the case with most economic and financial time series. A number of new results are derived in the paper: (a) The explicit form of the linear smoother based on the DCT, which is found to have time-varying weights and that uses all observations; (b) the extrapolation of the DCT-smoothed series; (c) the form of the average frequency response function, which is shown to approximate the frequency response of the ideal low pass filter; (d) the asymptotic distribution of the DCT coefficients under the assumptions of deterministic or stochastic trends; (e) two news method for selecting an appropriate degree of smoothing, in general and under the assumptions in (d). These findings are applied and illustrated using several real world economic and financial time series. The results indicate that the DCT-based smoother that is proposed can find many useful applications in economic and financial time series.
Similar content being viewed by others
References
Ahmed N, Natarajan T, and Rao K R, Discrete cosine transform, IEEE Trans. Comput., 1974, C-23: 90–93.
Unser M, On the approximation of the discrete Karhunen-Loeve transform for stationary processes, Signal Processing, 1984, 7: 231–249.
Chitprasert P and Rao K R, Discrete cosine transform filtering, Signal Processing, 1990, 19: 233–245.
Britanak V, Yip P C, and Rao K R, Discrete Cosine and Sine Transforms: General Properties, Fast Algorithms and Integer Approximations, Academic Press, 2006.
Kim D and De Wilde P, Performance analysis of the DCT-LMS adaptive filtering algorithm, Signal Processing, 2000, 80: 1629–1654.
Sherlock B G and Kakad Y P, Windowed discrete cosine and sine transforms for shifting data, Signal Processing, 2001, 81: 1465–1478.
Davies R, Integrated processes and the discrete cosine transform, Journal of Applied Probability, 2001, 38A: 701–717.
Hodrick R and Prescott E C, Postwar U.S. business cycles: An empirical investigation, Journal of Money, Credit and Banking, 1997, 29: 1–16.
King R G and Rebelo S T, Low frequency filtering and business cycles, Journal of Economic Dynamics and Control, 1993, 17: 207–232.
Baxter M and King R G, Measuring business-cycles: Approximate band-pass filters for economic time series, Review of Economics and Statistics, 1999, 81: 575–593.
Christiano L and Fitzgerald T, The band pass filter, International Economic Review, 2003, 44: 435–465.
Wildi M, Signal extraction, Lecture Notes in Economics and Mathematical Systems, Springer, 2005.
Pollock D S G, Trend estimation and de-trending via rational square-wave filters, Journal of Econometrics, 2000, 99: 317–334.
Bell W, Signal extraction for non-stationary time series, The Annals of Statistics, 1984, 12: 646–664.
Kohn R and Ansley C, Signal extraction for finite non-stationary time series, Biometrika, 1987, 74: 411–421.
McElroy T, Matrix Formulas for Nonstationary Signal Extraction, SRD Research Report No. RRS2005-04, U.S. Census Bureau, 2005.
Phillips P C B, Spurious Regression Unmasked, 1996, CFDP 1135.
Phillips P C B, Econometric Analysis of Fisher’s Equation, 1998, CFDP 1180.
Phillips P C B, Challenges of trending time series econometrics, Mathematics and Computers in Simulation, 2005, 68: 401–416.
Thomakos D D, Optimal Linear filtering, smoothing and trend extraction for processes with unit roots and cointegration, Working paper, SSRN, 2008a.
Golyandina N, Nekrutkin V, and Zhigljavsky A, Analysis of Time Series Structure: SSA and Related Techniques, Monographs on Statistics and Applied Probability, Chapman and Hall, 2001.
Thomakos D D, Optimal linear filtering, smoothing and trend extraction for M-period differences for processes with unit roots, working paper, SSRN, 2008b.
Hassanib H B and Zhigljavskyb A, Singular spectrum analysis: Methodology and application to economics data, Journal of Systems Science and Complexity, 2009, 22(3): 372–394.
Hassani H and Thomakos D, A review on singular spectrum analysis for economic and financial time series, Statistics and Its Interface, 2010, 3: 377–397.
Hassani H and Mahmoudvand R, Multivariate singular spectrum analysis: A general view and new vector forecasting approach, International Journal of Energy and Statistics, 2013, 1: 55–83.
Beneki C and Silva E S, Analyzing and forecasting european union energy data, International Journal of Energy and Statistics, 2013, 1: 127–141.
Wahba G, A survey of some smoothing problems and the method of generalized cross-validation for solving them, Applications of Statistics, Ed. by Krishnaiah P R, North-Holland, Amsterdam, 1977, 507–523.
Craven P and Wahba G, Smoothing noisy data with spline functions: Estimating the correct degree of smoothing by the method of generalized cross-validation, Numerische Mathematik, 1979, 31: 377–403.
Ghodsi M and Yarmohammadi M, Exchange rate forecasting with optimum singular spectrum analysis, Journal of Systems Science and Complexity, 2014, 27(1): 47–55.
Enezes M, Souza R C, and Pessanha J, Combining singular spectrum analysis and PAR(p) structures to model wind time series, Journal of System Science and Complexity, 2014, 27(1): 29–46.
Author information
Authors and Affiliations
Corresponding author
Additional information
This paper was recommended for publication by Editor WANG Shouyang.
Rights and permissions
About this article
Cite this article
Thomakos, D. Smoothing Non-Stationary Time Series Using the Discrete Cosine Transform. J Syst Sci Complex 29, 382–404 (2016). https://doi.org/10.1007/s11424-015-4071-7
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11424-015-4071-7