Electronic Journal of Statistics

Locally stationary functional time series

Anne van Delft and Michael Eichler

Full-text: Open access


The literature on time series of functional data has focused on processes of which the probabilistic law is either constant over time or constant up to its second-order structure. Especially for long stretches of data it is desirable to be able to weaken this assumption. This paper introduces a framework that will enable meaningful statistical inference of functional data of which the dynamics change over time. We put forward the concept of local stationarity in the functional setting and establish a class of processes that have a functional time-varying spectral representation. Subsequently, we derive conditions that allow for fundamental results from nonstationary multivariate time series to carry over to the function space. In particular, time-varying functional ARMA processes are investigated and shown to be functional locally stationary according to the proposed definition. As a side-result, we establish a Cramér representation for an important class of weakly stationary functional processes. Important in our context is the notion of a time-varying spectral density operator of which the properties are studied and uniqueness is derived. Finally, we provide a consistent nonparametric estimator of this operator and show it is asymptotically Gaussian using a weaker tightness criterion than what is usually deemed necessary.

Article information

Electron. J. Statist., Volume 12, Number 1 (2018), 107-170.

Received: May 2017
First available in Project Euclid: 15 January 2018

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 62M10: Time series, auto-correlation, regression, etc. [See also 91B84]
Secondary: 62M15: Spectral analysis

Functional data analysis locally stationary processes spectral analysis kernel estimator

Creative Commons Attribution 4.0 International License.


van Delft, Anne; Eichler, Michael. Locally stationary functional time series. Electron. J. Statist. 12 (2018), no. 1, 107--170. doi:10.1214/17-EJS1384. https://projecteuclid.org/euclid.ejs/1516006818

Export citation


  • Antoniadis, A., Paparoditis, E. and Sapatinas, T. (2006). A functional wavelet-kernel approach for time series prediction., Journal of the Royal Statistical Society Ser. B 86 837–857.
  • Antoniadis, A. and Sapatinas, T. (2003). Wavelet methods for continuous time predictions using Hilbert-valued autoregressive processes., Journal of Multivariate Analysis 87 133–158.
  • Aue, A., Dubart Norinho, D. and Hörmann, S. (2015). On the prediction of stationary functional time series., Journal of the American Statistical Association 110 378–392.
  • Aue, A. andvan Delft, A. (2017). Testing for stationarity of functional time series in the frequency domain. Preprint, https://arxiv.org/pdf/1701.01741.pdf.
  • Aue, A., Gabrys, R., Horváth, L. and Kokoszka, P. (2009). Estimation of a change-point in the mean function of functional data., Journal of Multivariate Analysis 100 2254–2269.
  • Benko, M., Härdle, W. and Kneip, A. (2009). Common functional component analysis., Annals of Statistics 37 1–34.
  • Berkes, I., Gabrys, R., Horváth, L. and Kokoszka, P. (2009). Detecting changes in the mean of functional observations., Journal of the Royal Statistical Society Ser. B 71 927–946.
  • Besse, P. and Ramsay, J. O. (1986). Principal components analysis of samples functions., Psychometrika 51 285–311.
  • Bogachev, V. I. and Miftakhov, A. F. (2015). On weak convergence of finite-dimensional and infinite-dimensional distributions of random processes. Preprint 15102, Collaborative Research Centre 701, University of, Bielefeld.
  • Bosq, D. (2000)., Linear Processes in Function Spaces. Springer, New York.
  • Bosq, D. (2002). Estimation of mean and covariance operator of autoregressive processes in Banach spaces., Statistical inference for Stochastic Processes 5 287–306.
  • Bosq, D. and Blanke, D. (2007)., Inference and Prediction in Large Dimensions. Wiley, Chichester.
  • Bowsher, C. G. and Meeks, R. (2008). The Dynamics of Economic Functions: Modeling and Forecasting the Yield Curve., Journal of the American Statistical Association 103 1419–1437.
  • Brillinger, D. R. (1981)., Time Series: Data Analysis and Theory. McGraw Hill, New York.
  • Brockwell, P. J. and Davis, R. A. (1991)., Time Series: Theory and Methods. Springer, New York.
  • Cardot, H. and Sarda, P. (2006). Linear regression models for functional data. In, The Art of Semiparametrics (S. Sperlich and G. Aydinli, eds.) 49–66. Springer, Heidelberg.
  • Cremers, H. and Kadelka, D. (1986). On weak convergence of integral functionals of stochastic processes with applications to processes taking paths in $L_p^E$., Stochastic Processes and Their Applications 305–317.
  • Dahlhaus, R. (1983). Spectral analysis with tapered data., Journal of Time Series Analysis 4 163–175.
  • Dahlhaus, R. (1988). Small sample effects in time series analysis:a new asymptotic theory and a new estimate., Annals of Statistics 16 808–841.
  • Dahlhaus, R. (1996a). On the Kullback-Leibler information divergence of locally stationary processes., Stochastic Process and their Applications 62 139–168.
  • Dahlhaus, R. (1996b)., Asymptotic statistical inference for nonstationary processes with evolutionary spectra. In: Robinson, P. M., Rosenblatt, M. (Eds.), Athens Conference on Applied Probability and Time Series Analysis, vol. II. Springer- Verlag, New York.
  • Dahlhaus, R. (1997). Fitting time series models to nonstationary processes., Annals of Statistics 25 1–37.
  • Dahlhaus, R. and Subba Rao, S. (2006). Statistical inference for time-varying ARCH processes., Annals of Statistics 34 1077–1114.
  • Damon, J. and Guillas, S. (1982). The inclusion of exogeneous variables in functional autoregressive ozone forecasting., Environmetrics 13 759–774.
  • Dauxois, J., Pousse, A. and Romain, Y. (1982). Asymptotic theory for the principal component analysis of a vector random function: some applications to statistical inference., Journal of Multivariate Analysis 12 136–154.
  • Dehling, H. and Sharipov, O. S. (2005). Estimation of mean and covariance operator for Banach space valued autoregressive processes with independent innovations., Statistical inference for stochastic processes 8 137–149.
  • Dunford, N. and Schwartz, J. T. (1958)., Linear Operators, Part I: General Theory. Wiley, New York.
  • Edwards, R. (1967)., Fourier series: a modern introduction. Holt, Rinehart and Winston, New York.
  • Eichler, M. (2007). A frequency-domain based test for independence between stationary time series., Metrika 65 133–157.
  • Erbas, B., Hyndman, R. J. and Gertig, D. M. (2007). Forecasting age-specific breast cancer mortality using functional data models., Statistics in Medicine 26 458–470.
  • Ferraty, F. and Vieu, P. (2006)., Nonparametric Functional Data Analysis. Springer, New York.
  • Gabrys, R., Hörmann, S. and Kokoszka, P. (2010). Monitoring the intraday volatility pattern. Technical Report, Utah State, University.
  • Grenander, U. (1981)., Abstract Inference. Wiley Series in Probability and Mathematical Statistics IX. John Wiley & Sons, New York.
  • Grinblat, L. Š. (1976). A limit theorem for measurable random processes and its applications., Proceedings of the American Mathematical Society 61 371–376.
  • Hays, S., Shen, H. and Huang, J. Z. (2012). Functional dynamic factor models with application to yield curve forecasting., Annals of Applied Statistics 6 870–894.
  • Hörmann, S., Horvàth, L. and Reeder, R. (2013). A functional version of the ARCH model., Econometric Theory 29 267–288.
  • Hörmann, S., Kidziński, L. and Hallin, M. (2015). Dynamic functional principal components., The Royal Statistical Society: Series B 77 319–348.
  • Hörmann, S. and Kokoszka, P. (2010). Weakly dependent functional data., The Annals of Statistics 38 1845–1884.
  • Horváth, L., Hušková, M. and Kokoszka, P. (2010). Testing the stability of the functional autoregressive process., Journal of Multivariate Analysis 21 352–367.
  • Hyndman, R. J. and Booth, H. (2008). Stochastic population forecasts using functional data models for mortality, fertility and migration., International Journal of Forecasting 24 323–342.
  • Hyndman, R. J. and Ullah, M. S. (2007). Robust forecasting of mortality and fertility rates: A functional data approach., Computational Statistics and Data Analysis 51 4942–4956.
  • Karhunen, K. (1947). Über lineare Methoden in der Wahrscheinlichkeitsrechnung., Annales Academiae Scientiarium Fennicae, Ser. A.I. Math.-Phys. 37 1–79.
  • Kleffe, J. (1973). Principal components of random variables with values in a separable Hilbert space., Mathematische Operationsforschung Statistik 5 391–406.
  • Künsch, H. R. (1995). A note on causal solution for locally stationary AR processes. Preprint, ETH, Zurich.
  • Loève, M. (1948)., Fonctions aléotoires du second ordre. Supplement to P. Lévy, Processus stochastiques et Mouvement Brownian. Gauthier-Villars, Paris.
  • Martin, W. and Flandrin, P. (1985). Wigner-Ville spectral analysis of nonstationary processes., IEEE Trans. Signal Process 33 1461–1470.
  • Mas, A. (2000). Estimation d’opérateurs de corrélation de processus linéaires fonctionnels: lois limites, déviations modérées, PhD thesis, Université Paris, VI.
  • Müller, H. G. and Yao, F. (2008). Functional additive models., Journal of the American Statistical Association 103 1534–1544.
  • Murphy, G. J. (1990)., $C^*$-algebras and Operator Theory. Academic Press.
  • Nelson, E. (1969)., Topics in Dynamics, Volume I: Flows. University Press, Princeton.
  • Panaretos, V. M. and Tavakoli, S. (2013a). Cramér-Karhunen-Loève representation and harmonic analysis of functional time series., Stochastic Processes and their Applications 123 2779–2807.
  • Panaretos, V. M. and Tavakoli, S. (2013b). Fourier analysis of stationary time series in function space., The Annals of Statistics 41 568–603.
  • Priestley, M. B. (1981)., Spectral Analysis and Time Series, Vol. 2. Academic Press, London.
  • Ramsay, J. O. and Silverman, B. W. (2005)., Functional Data Analysis, 2nd ed. Springer, New York.
  • van Delft, A. and Eichler, M. (2015). Data-adaptive estimation of time-varying spectral densities. Preprint Maastricht University, https://arxiv.org/pdf/1512.00825.pdf.
  • van Delft, A. and Eichler, M. (2018). A note on Herglotz’s theorem for time series on function spaces. ArXiv, preprint.
  • Vogt, M. (2012). Nonparametric regression for locally stationary time series., Annals of Statistics 40 2601–2633.
  • Yao, F., Müller, H. G. and Wang, L. J (2005). Functional linear regression for longitudinal data., Annals of Statistics 33 2873–2903.