1932
0
  1. Home
  2. A-Z Publications
  3. Annual Review of Statistics and Its Application
  4. Volume 7, 2020
  5. Article

Annual Review of Statistics and Its Application

Volume 7, 2020

Nonparametric Spectral Analysis of Multivariate Time Series

Abstract

Spectral analysis of multivariate time series has been an active field of methodological and applied statistics for the past 50 years. Since the success of the fast Fourier transform algorithm, the analysis of serial auto- and cross-correlation in the frequency domain has helped us to understand the dynamics in many serially correlated data without necessarily needing to develop complex parametric models. In this work, we give a nonexhaustive review of the mostly recent nonparametric methods of spectral analysis of multivariate time series, with an emphasis on model-based approaches. We try to give insights into a variety of complimentary approaches for standard and less standard situations (such as nonstationary, replicated, or high-dimensional time series), discuss estimation aspects (such as smoothing over frequency), and include some examples stemming from life science applications (such as brain data).

Keyword(s): coherency, Fourier, locally stationary time series, positive-definiteness, smoothing, wavelets
Loading

Article metrics loading...

/content/journals/10.1146/annurev-statistics-031219-041138
2020-03-07
2025-04-26
Loading full text...

Full text loading...

/deliver/fulltext/statistics/7/1/annurev-statistics-031219-041138.html?itemId=/content/journals/10.1146/annurev-statistics-031219-041138&mimeType=html&fmt=ahah

Literature Cited

  1. Adak S 1998. Time-dependent spectral analysis of non-stationary time series. J. Am. Stat. Assoc. 93:1488–501
     [Google Scholar]
  2. Barigozzi M, Cho H, Fryzlewicz P 2018. Simultaneous multiple change-point and factor analysis for high-dimensional time series. J. Econometr. 206:187–225
     [Google Scholar]
  3. Birr S, Volgushev S, Hallin M, Kley T, Dette H 2017. Quantile spectral analysis for locally stationary time series. J. R. Stat. Soc. B 79:1619–43
     [Google Scholar]
  4. Böhm H, Ombao H, von Sachs R, Sanes J 2010. Classification of multivariate non-stationary signals: the SLEX-shrinkage approach. J. Stat. Plan. Inference 140:3754–63
     [Google Scholar]
  5. Böhm H, von Sachs R 2008. Structural shrinkage of nonparametric spectral estimators for multivariate time series. Electron. J. Stat. 2:696–721
     [Google Scholar]
  6. Böhm H, von Sachs R 2009. Shrinkage estimation in the frequency domain of multivariate time series. J. Multivar. Anal. 100:913–35
     [Google Scholar]
  7. Brillinger D 1981. Time Series: Data Analysis and Theory San Francisco: Holden-Day
     [Google Scholar]
  8. Brockwell P, Davis R 1991. Time Series: Theory and Methods New York: Springer
     [Google Scholar]
  9. Bühlmann P 1996. Locally adaptive lag-window spectral estimation. J. Time Ser. Anal. 17:247–70
     [Google Scholar]
  10. Chau J 2018. pdSpecEst: Positive-definite wavelet-based multivariate spectral analysis. R package , version 1.2.3. https://CRAN.R-project.org/package=pdSpecEst
     [Google Scholar]
  11. Chau J, Ombao H, von Sachs R 2019. Intrinsic data depth for Hermitian positive definite matrices. J. Comput. Graph. Stat. 28:427–39
     [Google Scholar]
  12. Chau J, von Sachs R 2016. Functional mixed effects wavelet estimation for spectra of replicated time series. Electron. J. Stat. 10:2461–510
     [Google Scholar]
  13. Chau J, von Sachs R 2019. Intrinsic wavelet regression for curves of Hermitian positive definite matrices. J. Am. Stat. Assoc. https://doi.org/10.1080/01621459.2019.1700129
    [Crossref] [Google Scholar]
  14. Chau J, von Sachs R 2018. Intrinsic wavelet regression for surfaces of Hermitian positive definite matrices. arXiv:1808.08764 [stat.ME]
    [Google Scholar]
  15. Cho H, Fryzlewicz P 2015. Multiple change-point detection for high-dimensional time series via sparsified binary segmentation. J. R. Stat. Soc. B 77:475–507
     [Google Scholar]
  16. Cooley J, Tukey J 1965. An algorithm for the machine calculation of complex Fourier series. Math. Comput. 90:297–301
     [Google Scholar]
  17. Dahlhaus R 1997. Fitting time series models to nonstationary processes. Ann. Stat. 25:1–37
     [Google Scholar]
  18. Dahlhaus R 2000a. A likelihood approximation for locally stationary processes. Ann. Stat. 28:1762–94
     [Google Scholar]
  19. Dahlhaus R 2000b. Graphical interaction models for multivariate time series. Metrika 51:157–72
     [Google Scholar]
  20. Dahlhaus R 2012. Locally stationary processes. In Time Series Analysis: Methods and Applications T Subba Rao, S Subba Rao, CR Rao351–413 Amsterdam: Elsevier
     [Google Scholar]
  21. Dahlhaus R, Neumann M 2001. Locally adaptive fitting of semiparametric models to nonstationary time series. Stoch. Process. Appl. 91:277–308
     [Google Scholar]
  22. Dahlhaus R, Polonik W 2006. Nonparametric quasi maximum likelihood estimation for Gaussian locally stationary processes. Ann. Stat. 34:2790–824
     [Google Scholar]
  23. Dahlhaus R, Richter S, Wu WB 2019. Towards a general theory for nonlinear locally stationary processes. Bernoulli 25:1013–44
     [Google Scholar]
  24. Dahlhaus R, Subba Rao S 2006. Statistical inference for time-varying ARCH processes. Ann. Stat. 34:1075–114
     [Google Scholar]
  25. Dai M, Guo W 2004. Multivariate spectral analysis using Cholesky decomposition. Biometrika 91:629–43
     [Google Scholar]
  26. Davis R, Lee TCM, Rodriguez-Yam G 2006. Structural break estimation for non-stationary time series models. J. Am. Stat. Assoc. 101:223–39
     [Google Scholar]
  27. Davis R, Mikosch T, Zhao Y 2013. Measures of serial extremal dependence and their estimation. Stoch. Process. Appl. 123:2575–602
     [Google Scholar]
  28. Dette H, Hallin M, Kley T, Volgushev S 2015. Of copulas, quantiles, ranks and spectra: An approach to spectral analysis. Bernoulli 21:781–831
     [Google Scholar]
  29. Dette H, Paparoditis E 2009. Bootstrapping frequency domain tests in multivariate time series with an application to comparing spectral densities. J. R. Stat. Soc. B 71:831–57
     [Google Scholar]
  30. Eichler M 2012. Graphical modelling of multivariate time series. Probab. Theory Relat. Fields 153:233–68
     [Google Scholar]
  31. Eichler M, Motta G, von Sachs R 2011. Fitting dynamic factor models to non-stationary time series. J. Econom. 163:51–70
     [Google Scholar]
  32. Fan J, Gijbels I 1992. Local Polynomial Modelling and Its Applications London: Chapman & Hall
     [Google Scholar]
  33. Fiecas M, Franke J, von Sachs R, Tadjuidje J 2017. Shrinkage estimation for multivariate hidden Markov mixture models. J. Am. Stat. Assoc. 112:424–35
     [Google Scholar]
  34. Fiecas M, Ombao H 2011. The generalized shrinkage estimator for the analysis of functional connectivity of brain signals. Ann. Appl. Stat. 5:1102–25
     [Google Scholar]
  35. Fiecas M, Ombao H 2016. Modeling the evolution of dynamic brain processes during an associative learning experiment. J. Am. Stat. Assoc. 111:1440–53
     [Google Scholar]
  36. Fiecas M, von Sachs R 2014. Data-driven shrinkage of the spectral density matrix of a high-dimensional time series. Electron. J. Stat. 8:2975–3003
     [Google Scholar]
  37. Forni M, Hallin M, Lippi M, Reichlin L 2000. Fitting dynamic factor models to non-stationary time series. Rev. Econ. Stat. 82:540–54
     [Google Scholar]
  38. Franke J, Härdle W 1992. On bootstrapping kernel spectral estimates. Ann. Stat. 20:121–45
     [Google Scholar]
  39. Freyermuth JM, Ombao H, von Sachs R 2010. Tree-structured wavelet estimation in a mixed effects model for spectra of replicated time series. J. Am. Stat. Assoc. 105:634–46
     [Google Scholar]
  40. Fryzlewicz P, Nason G, von Sachs R 2008. A wavelet-Fisz approach to spectrum estimation. J. Time Ser. Anal. 29:868–80
     [Google Scholar]
  41. Gao H 1997. Choice of thresholds for wavelet shrinkage estimate of the spectrum. J. Time Ser. Anal. 18:231–51
     [Google Scholar]
  42. Gorrostieta C, Ombao H, Prado R, Patel S, Eskandar E 2012. Exploring dependence between brain signals in a monkey during learning. J. Time Ser. Anal. 33:771–78
     [Google Scholar]
  43. Gorrostieta C, Ombao H, von Sachs R 2019. Time-dependent dual-frequency coherence in multivariate non-stationary time series. J. Time Ser. Anal. 40:3–22
     [Google Scholar]
  44. Guo W, Dai M 2006. Multivariate time-dependent spectral analysis using Cholesky decomposition. Stat. Sin. 16:825–45
     [Google Scholar]
  45. Hörmann S, Kidzin'ski L, Hallin M 2015. Dynamic functional principal components. J. R. Stat. Soc. B 77:319–48
     [Google Scholar]
  46. Huang HY, Ombao H, Stoffer D 2004. Discrimination and classification of nonstationary time series using the SLEX model. J. Am. Stat. Assoc. 99:763–74
     [Google Scholar]
  47. Jansen M, Oonincx P 2005. Second Generation Wavelets and Applications London: Springer
     [Google Scholar]
  48. Jentsch C, Kreiss JP 2010. The multiple hybrid bootstrap resampling multivariate linear processes. J. Multivar. Anal. 101:2320–45
     [Google Scholar]
  49. Kakizawa Y, Shumway R, Taniguchi M 1998. Discrimination and clustering for multivariate time series. J. Am. Stat. Assoc. 441:328–40
     [Google Scholar]
  50. Kirch C, Politis DN 2011. TFT-bootstrap: resampling time series in the frequency domain to obtain replicates in the time domain. Ann. Stat. 39:1427–70
     [Google Scholar]
  51. Koopmans J 1974. The Spectral Analysis of Time Series Amsterdam: Elsevier
     [Google Scholar]
  52. Krafty R, Collinge W 2013. Penalized multivariate Whittle likelihood for power spectrum estimation. Biometrika 100:447–58
     [Google Scholar]
  53. Krafty R, Hall M, Guo W 2011. Functional mixed effects spectral analysis. Biometrika 98:583–98
     [Google Scholar]
  54. Krafty R, Xiong S, Stoffer D, Buysse D, Hall M 2012. Enveloping spectral surfaces: covariate dependent spectral analysis of categorical time series. J. Time Ser. Anal. 33:797–806
     [Google Scholar]
  55. Kreiss JP, Paparoditis E 2020. Bootstrap for Time Series: Theory and Applications New York: Springer. In press
     [Google Scholar]
  56. Ledoit O, Wolf M 2004. A well-conditioned estimator for large-dimensional covariance matrices. J. Multivar. Anal. 88:365–411
     [Google Scholar]
  57. Ledoit O, Wolf M 2012. Nonlinear shrinkage estimation of large-dimensional covariance matrices. Ann. Stat. 40:1024–60
     [Google Scholar]
  58. Ledoit O, Wolf M 2017. Analytical nonlinear shrinkage of large-dimensional covariance matrices Work. Pap. No. 264, Dep. Econ., Univ. Zurich
    [Google Scholar]
  59. Lii K, Rosenblatt M 2002. Spectral analysis for harmonizable processes. Ann. Stat. 30:258–97
     [Google Scholar]
  60. Martin W, Flandrin P 1995. Wigner–Ville spectral analysis of nonstationary processes. IEEE Trans. Signal Process. 33:1461–70
     [Google Scholar]
  61. Moulin P 1994. Wavelet thresholding techniques for power spectrum estimation. IEEE Trans. Signal Process. 42:3126–36
     [Google Scholar]
  62. Nason G 2008. Wavelet Methods in Statistics with R New York: Springer
     [Google Scholar]
  63. Nason G, Silverman B 1995. The stationary wavelet transform and some statistical applications. In Wavelets and Statistics A Antoniadis, G Oppenheim281–300 New York: Springer
     [Google Scholar]
  64. Nason G, von Sachs R, Kroisandt G 2000. Wavelet processes and adaptive estimation of the evolutionary wavelet spectrum. J. R. Stat. Soc. B 62:271–92
     [Google Scholar]
  65. Neumann M 1996. Spectral density estimation via nonlinear wavelet methods for stationary non-Gaussian time series. J. Time Ser. Anal. 17:601–33
     [Google Scholar]
  66. Neumann M, von Sachs R 1997. Wavelet thresholding in anisotropic function classes and application to adaptive estimation of evolutionary spectra. Ann. Stat. 25:38–76
     [Google Scholar]
  67. Ombao H, Raz J, von Sachs R, Guo W 2002. The SLEX model of a non-stationary random process. Ann. Inst. Stat. Math. 54:171–200
     [Google Scholar]
  68. Ombao H, Raz J, von Sachs R, Mallow B 2001. Automatic analysis of bivariate non-stationary time series. J. Am. Stat. Assoc. 96:543–60
     [Google Scholar]
  69. Ombao H, von Sachs R, Guo W 2005. SLEX analysis of multivariate non-stationary time series. J. Am. Stat. Assoc. 100:519–31
     [Google Scholar]
  70. Panaretos V, Tavakoli S 2013. Fourier analysis of stationary time series in function space. Ann. Stat. 41:568–603
     [Google Scholar]
  71. Park T, Eckley I, Ombao H 2014. Estimating time-evolving partial coherence between signals via multivariate locally stationary wavelet processes. IEEE Trans. Signal Process. 62:5240–50
     [Google Scholar]
  72. Parzen E 1985. Time series model identification and quantile spectral analysis. IFAC Proc. Vol. 18:731–36
     [Google Scholar]
  73. Pourahmadi M 2011. Covariance estimation: the GLM and regularization perspectives. Stat. Sci. 26:369–87
     [Google Scholar]
  74. Priestley M 1965. Evolutionary spectra and non-stationary processes. J. R. Stat. Soc. B 27:204–37
     [Google Scholar]
  75. Rahman I, Drori I, Stodden V, Donoho D, Schröder P 2005. Multiscale representations for manifold-valued data. Multiscale Model. Simul. 4:1201–32
     [Google Scholar]
  76. Rosen O, Stoffer D 2007. Automatic estimation of multivariate spectra via smoothing splines. Biometrika 94:335–45
     [Google Scholar]
  77. Rosen O, Stoffer D, Wood S 2009. Local spectral analysis via a Bayesian mixture of smoothing splines. J. Am. Stat. Assoc. 104:249–62
     [Google Scholar]
  78. Rosen O, Stoffer D, Wood S 2012. Adaptspec: adaptive spectral estimation for nonstationary time series. J. Am. Stat. Assoc. 107:1575–89
     [Google Scholar]
  79. Roueff F, von Sachs R 2019. Time-frequency analysis of locally stationary Hawkes processes. Bernoulli 25:1355–85
     [Google Scholar]
  80. Roueff F, von Sachs R, Sansonnet L 2016. Locally stationary Hawkes processes. Stoch. Process. Appl. 126:1710–43
     [Google Scholar]
  81. Sakiyama K, Taniguchi M 2004. Discriminant analysis for locally stationary processes. J. Multivar. Anal. 90:282–300
     [Google Scholar]
  82. Sanderson J, Fryzlewicz P, Jones M 2010. Estimating linear dependence between nonstationary time series using the locally stationary wavelet model. Biometrika 97:435–46
     [Google Scholar]
  83. Shumway R 2003. Time-frequency clustering and discriminant analysis. Stat. Probab. Lett. 63:307–14
     [Google Scholar]
  84. Shumway R, Stoffer D 2006. Time Series Analysis and Its Applications New York: Springer
     [Google Scholar]
  85. Stoffer D 2015. Spectral analysis of qualitative time series. Handbook of Discrete-Valued Time Series RA Davis, SH Holan, R Lund, N Ravishanker287–309 London: CRC Press
     [Google Scholar]
  86. Subba Rao S 2018. Orthogonal samples for estimators in time series. J. Time Ser. Anal. 39:313–37
     [Google Scholar]
  87. Thomson D 1982. Spectrum estimation and harmonic analysis. Proc. IEEE 70:1055–96
     [Google Scholar]
  88. van Delft A, Eichler M 2018. Locally stationary functional time series. Electron. J. Stat. 12:107–70
     [Google Scholar]
  89. von Sachs R 1994. Peak-insensitive nonparametric spectrum estimation. J. Time Ser. Anal. 15:429–52
     [Google Scholar]
  90. Wahba G 1980. Automatic smoothing of the log periodogram. J. Am. Stat. Assoc. 75:122–32
     [Google Scholar]
  91. Walden AT 2000. A unified view of multitaper multivariate spectral estimation. Biometrika 87:767–88
     [Google Scholar]
  92. Wang Y, Ting CM, Ombao H 2017. Estimating dynamic connectivity states in fMRI using regime-switching factor models. IEEE Trans. Med. Imaging 37:1011–23
     [Google Scholar]
  93. Welch P 1967. The use of Fast Fourier Transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms. IEEE Trans. Audio Electroacoust. 15:70–73
     [Google Scholar]
  94. Wu WB, Zaffaroni P 2018. Asymptotic theory for spectral density estimates of general multivariate time series. Econometr. Theory 34:1–22
     [Google Scholar]
  95. Wu WB, Zhou Z 2011. Gaussian approximations for non-stationary multiple time series. Stat. Sin. 21:1397–413
     [Google Scholar]
  96. Yuan Y, Zhu H, Lin W, Marron J 2012. Local polynomial regression for symmetric positive definite matrices. J. R. Stat. Soc. B 74:697–719
     [Google Scholar]
/content/journals/10.1146/annurev-statistics-031219-041138
Loading
Nonparametric Spectral Analysis of Multivariate Time Series
Annual Review of Statistics and Its Application 7, 361 (2020); https://doi.org/10.1146/annurev-statistics-031219-041138
/content/journals/10.1146/annurev-statistics-031219-041138
/content/journals/10.1146/annurev-statistics-031219-041138
Loading

Data & Media loading...

  • Article Type: Review Article

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error