Abstract
Within the series of singular spectrum analysis (SSA) methods, there exist several versions of forecasting algorithms for signals corrupted by additive noise. In this paper, a technique is proposed to estimate the asymptotic accuracy of the recurrent version of such forecasting when the length of a series tends to infinity. Most elements of this construction can be reduced to already studied and published results, although some of them are hard to implement in specific situations. The article brings together all these elements and augments and comments on them. Several examples of determining estimates of accuracy for a recurrent forecast are given for specific signals and noises. The computational experiments carried out confirm the theoretical results.
REFERENCES
N. Golyandina, V. Nekrutkin, and A. Zhigljavsky, Analysis of Time Series Structure. SSA and Related Techniques (Chapman & Hall/CRC, New York, 2001).
N. Golyandina and A. Zhigljavsky, Singular Spectrum Analysis for Time Series, 2nd ed. (Springer-Verlag, Berlin, 2020), in Ser.: Springer Briefs in Statistics.
P. P. Vaidyanathan, The Theory of Linear Prediction (Morgan & Claypool, San Rafael, Calif., 2008).
V. Nekrutkin, “Perturbation expansions of signal subspaces for long signals,” Stat. Its Interface 3, 297–319 (2010).
N. Golyandina, “On the choice of parameters in Singular Spectrum Analysis and related subspace-based methods,” Stat. Its Interface 3, 259–279 (2010).
E. Ivanova and V. Nekrutkin, “Two asymptotic approaches for the exponential signal and harmonic noise in Singular Spectrum Analysis,” Stat. Its Interface 12, 49–59 (2019). https://doi.org/10.4310/SII.2019.v12.n1.a5
N. V. Zenkova and V. V. Nekrutkin, “On the asymptotical separation of linear signals from harmonics by Singular Spectrum Analysis,” Vestn. St Petersburg Univ.: Math. 55, 166–173 (2022). https://doi.org/10.1134/S1063454122020157
ACKNOWLEDGMENTS
I am grateful to the reviewers, whose remarks undoubtedly contributed to improvement of the manuscript.
Funding
This work was supported by the Russian Foundation for Basic Research, project no. 20-01-00067.
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated by I. Nikitin
APPENDIX. COMPUTER EXPERIMENTS
APPENDIX. COMPUTER EXPERIMENTS
In this section we present several variants of computer experiments that illustrate the theoretical results of Subsection 3.4. As already mentioned, the considered series have the form xn = fn + δen, 1 ≤ n ≤ N, and the problem lies in forecasting the signal value \({{f}_{{N + k}}}\), k ≥ 1.
We consider three variants of the signal fn:
1. Exponential signal (EXP): fn = an, a = 1.01, and δ = 1.
2. Linear signal (LIN): fn = an + b, a = 0.5, b = 1, and δ = 0.5.
3. Harmonic signal (COS): fn = cos(2πω0n) with ω0 = \(\sqrt 2 {\text{/2}}\), and δ = 0.5.
In all cases, the noise has the form en = cos(2πωn) with ω = \(\sqrt 3 {\text{/2}}\).
As before, \({{\tilde {f}}_{{N + k}}}\) denotes the value of the recurrent forecast of \({{f}_{{N + k}}}\), and \(\Delta _{k}^{{(f)}}(N)\) = \(\left| {{{{\tilde {f}}}_{{N + k}}} - {{f}_{{N + k}}}} \right|\) is the k-step forecast error.
k-Step forecast, 1 ≤ k ≤ 50. Figure 1 is of preliminary character. It shows k-step forecasting errors for exponential (EXP), harmonic (COS), and linear (LIN) signals for N = 500, L = M = 250, and k = 1(1)50. We note that these errors exhibit very smooth behavior for EXP and LIN, while \(\Delta _{k}^{{(f)}}(N)\) strongly oscillates for COS.
Therefore, below we illustrate the behavior of \(\Delta _{1}^{{(f)}}(N)\) as a function of N for exponential and linear signals, and take the characteristic \(\left( {\sum\nolimits_{k = 1}^{10} {\Delta _{k}^{{(f)}}(N)} } \right){\text{/}}10\) to illustrate the forecasting behavior for a harmonic signal.
We note that in all the following experiments, we use the series lengths N = 50(50)1000 and L = M = N/2.
Exponential signal. Figure 2 shows the behavior of one-step forecasting errors as a function of the series length N for an exponential signal and harmonic noise.
The theoretical results of Section 3.4 show that \(\Delta _{1}^{{(f)}}(N)\) = O(1). Judging by Fig. 2, this estimate is quite accurate: starting from about N = 300, the values of \(\Delta _{1}^{{(f)}}(N)\) do not show an obvious tendency toward a decrease.
Linear signal. As already mentioned, for a linear signal, the expected estimate for \(\Delta _{1}^{{(f)}}(N)\) is O(N–1/2). Figures 3 and 4 confirm this theoretical result.
Harmonic signal. According to the results of Subsection 3.4, the expected upper bound for one-step forecast errors for a harmonic signal is O(N–1/2). Figures 5 and 6 show that the actual convergence rate may be O(N–1).
About this article
Cite this article
Nekrutkin, V.V. Remark on the Accuracy of Recurrent Forecasting in Singular Spectrum Analysis. Vestnik St.Petersb. Univ.Math. 56, 35–45 (2023). https://doi.org/10.1134/S1063454123010090
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1063454123010090