Smoothing Non-Stationary Time Series Using the Discrete Cosine Transform

被引:4
|
作者
Thomakos, Dimitrios [1 ,2 ]
机构
[1] Univ Peloponnese, Dept Econ, Athens 22100, Greece
[2] Rimini Ctr Econ Anal, Rimini, Italy
关键词
Discrete cosine transform; non-stationary time series; order selection; singular spectrum analysis; smoothing; trend extraction; unit root; SINGULAR SPECTRUM ANALYSIS; BUSINESS CYCLES; SIGNAL EXTRACTION; FILTERS;
D O I
10.1007/s11424-015-4071-7
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
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.
引用
收藏
页码:382 / 404
页数:23
相关论文
共 50 条
  • [41] Forecasting non-stationary economic time series.
    Öller, LE
    INTERNATIONAL JOURNAL OF FORECASTING, 2001, 17 (01) : 133 - 134
  • [42] Scaling in non-stationary time series. (I)
    Ignaccolo, M
    Allegrini, P
    Grigolini, P
    Hamilton, P
    West, BJ
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2004, 336 (3-4) : 595 - 622
  • [43] Non-stationary time series and the robustness of circadian rhythms
    Refinetti, R
    JOURNAL OF THEORETICAL BIOLOGY, 2004, 227 (04) : 571 - 581
  • [44] GAUSSIAN APPROXIMATIONS FOR NON-STATIONARY MULTIPLE TIME SERIES
    Wu, Wei Biao
    Zhou, Zhou
    STATISTICA SINICA, 2011, 21 (03) : 1397 - 1413
  • [45] Inference for non-stationary time-series autoregression
    Zhou, Zhou
    JOURNAL OF TIME SERIES ANALYSIS, 2013, 34 (04) : 508 - 516
  • [46] Generalized subsampling procedure for non-stationary time series
    Lenart, Lukasz
    ELECTRONIC JOURNAL OF STATISTICS, 2018, 12 (02): : 3875 - 3907
  • [47] Marked empirical processes for non-stationary time series
    Chan, Ngai Hang
    Zhang, Rongmao
    BERNOULLI, 2013, 19 (5A) : 2098 - 2119
  • [48] Comparing non-stationary and irregularly spaced time series
    Salcedo, Gladys E.
    Porto, Rogerio F.
    Morettin, Pedro A.
    COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2012, 56 (12) : 3921 - 3934
  • [49] Artificial neural networks for non-stationary time series
    Kim, TY
    Oh, KJ
    Kim, CH
    Do, JD
    NEUROCOMPUTING, 2004, 61 : 439 - 447
  • [50] Fast Two-Dimensional Smoothing with Discrete Cosine Transform
    Lyubin, Pavel
    Shchetinin, Eugeny
    DISTRIBUTED COMPUTER AND COMMUNICATION NETWORKS, DCCN 2016, 2016, 678 : 646 - 656