IDEAS home Printed from https://ideas.repec.org/p/aiz/louvad/2024004.html
   My bibliography  Save this paper

Time-Varying Covariance Matrices Estimation by Nonlinear Wavelet Thresholding in a Log-Euclidean Riemannian Manifold

Author

Listed:
  • Bailly, Gabriel

    (Université catholique de Louvain, LIDAM/ISBA, Belgium)

  • von Sachs, Rainer

    (Université catholique de Louvain, LIDAM/ISBA, Belgium)

Abstract

We tackle the problem of estimating time-varying covariance matrices (TVCM; i.e. covariance matrices with entries being time-dependent curves) whose elements show inhomogeneous smoothness over time (e.g. pronounced local peaks). To address this challenge, wavelet denoising estimators are particularly appropriate. Specifically, we model TVCM using a signal-noise model within the Riemannian manifold of symmetric positive definite matrices (endowed with the log-Euclidean metric) and use the intrinsic wavelet transform, designed for curves in Riemannian manifolds. Within this non-Euclidean framework, the proposed estimators preserve positive definiteness. Although linear wavelet estimators for smooth TVCM achieve good results in various scenarios, they are less suitable if the underlying curve features singularities. Consequently, our estimator is designed around a nonlinear thresholding scheme, tailored to the characteristics of the noise in covariance matrix regression models. The effectiveness of this novel nonlinear scheme is assessed by deriving mean-squared error consistency and by numerical simulations, and its practical application is demonstrated on TVCM of electroencephalography (EEG) data showing abrupt transients over time.

Suggested Citation

  • Bailly, Gabriel & von Sachs, Rainer, 2024. "Time-Varying Covariance Matrices Estimation by Nonlinear Wavelet Thresholding in a Log-Euclidean Riemannian Manifold," LIDAM Discussion Papers ISBA 2024004, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
  • Handle: RePEc:aiz:louvad:2024004
    as

    Download full text from publisher

    File URL: https://dial.uclouvain.be/pr/boreal/en/object/boreal%3A284862/datastream/PDF_01/view
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Michael H. Neumann, 1996. "Spectral Density Estimation Via Nonlinear Wavelet Methods For Stationary Non‐Gaussian Time Series," Journal of Time Series Analysis, Wiley Blackwell, vol. 17(6), pages 601-633, November.
    2. Joris Chau & Rainer von Sachs, 2021. "Intrinsic Wavelet Regression for Curves of Hermitian Positive Definite Matrices," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 116(534), pages 819-832, April.
    3. Chau, Joris & von Sachs, Rainer, 2022. "Time-varying spectral matrix estimation via intrinsic wavelet regression for surfaces of Hermitian positive definite matrices," Computational Statistics & Data Analysis, Elsevier, vol. 174(C).
    4. Ombao, Hernando & von Sachs, Rainer & Guo, Wensheng, 2005. "SLEX Analysis of Multivariate Nonstationary Time Series," Journal of the American Statistical Association, American Statistical Association, vol. 100, pages 519-531, June.
    5. Grant Hillier & Raymond Kan, 2021. "Moments of a Wishart Matrix," Journal of Quantitative Economics, Springer;The Indian Econometric Society (TIES), vol. 19(1), pages 141-162, December.
    6. Krebs, Johannes & Rademacher, Daniel & von Sachs, Rainer, 2022. "Statistical inference for intrinsic wavelet estimators of SPD covariance matrices in a log-Euclidean manifold," LIDAM Discussion Papers ISBA 2022004, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    7. Ying Yuan & Hongtu Zhu & Weili Lin & J. S. Marron, 2012. "Local polynomial regression for symmetric positive definite matrices," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 74(4), pages 697-719, September.
    8. Zhu, Hongtu & Chen, Yasheng & Ibrahim, Joseph G. & Li, Yimei & Hall, Colin & Lin, Weili, 2009. "Intrinsic Regression Models for Positive-Definite Matrices With Applications to Diffusion Tensor Imaging," Journal of the American Statistical Association, American Statistical Association, vol. 104(487), pages 1203-1212.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Chau, Joris & von Sachs, Rainer, 2022. "Time-varying spectral matrix estimation via intrinsic wavelet regression for surfaces of Hermitian positive definite matrices," Computational Statistics & Data Analysis, Elsevier, vol. 174(C).
    2. von Sachs, Rainer, 2019. "Spectral Analysis of Multivariate Time Series," LIDAM Discussion Papers ISBA 2019008, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    3. Emil Cornea & Hongtu Zhu & Peter Kim & Joseph G. Ibrahim, 2017. "Regression models on Riemannian symmetric spaces," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 79(2), pages 463-482, March.
    4. Krebs, Johannes & Rademacher, Daniel & von Sachs, Rainer, 2022. "Statistical inference for intrinsic wavelet estimators of SPD covariance matrices in a log-Euclidean manifold," LIDAM Discussion Papers ISBA 2022004, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    5. Chau, Van Vinh & von Sachs, Rainer, 2016. "Functional mixed effects wavelet estimation for spectra of replicated time series," LIDAM Discussion Papers ISBA 2016013, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    6. Chau, Van Vinh & von Sachs, Rainer, 2018. "Intrinsic wavelet regression for surfaces of Hermitian positive definite matrices," LIDAM Discussion Papers ISBA 2018025, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    7. Zhou Lan & Brian J. Reich & Joseph Guinness & Dipankar Bandyopadhyay & Liangsuo Ma & F. Gerard Moeller, 2022. "Geostatistical modeling of positive‐definite matrices: An application to diffusion tensor imaging," Biometrics, The International Biometric Society, vol. 78(2), pages 548-559, June.
    8. Ian L. Dryden & Kwang-Rae Kim & Huiling Le, 2019. "Bayesian Linear Size-and-Shape Regression with Applications to Face Data," Sankhya A: The Indian Journal of Statistics, Springer;Indian Statistical Institute, vol. 81(1), pages 83-103, February.
    9. Kwang‐Rae Kim & Ian L. Dryden & Huiling Le & Katie E. Severn, 2021. "Smoothing splines on Riemannian manifolds, with applications to 3D shape space," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 83(1), pages 108-132, February.
    10. Giovanni Motta & Hernando Ombao, 2012. "Evolutionary Factor Analysis of Replicated Time Series," Biometrics, The International Biometric Society, vol. 68(3), pages 825-836, September.
    11. Rabi Bhattacharya & Rachel Oliver, 2019. "Nonparametric Analysis of Non-Euclidean Data on Shapes and Images," Sankhya A: The Indian Journal of Statistics, Springer;Indian Statistical Institute, vol. 81(1), pages 1-36, February.
    12. Zhibiao Zhao, 2015. "Inference for Local Autocorrelations in Locally Stationary Models," Journal of Business & Economic Statistics, Taylor & Francis Journals, vol. 33(2), pages 296-306, April.
    13. Xiongtao Dai & Zhenhua Lin & Hans‐Georg Müller, 2021. "Modeling sparse longitudinal data on Riemannian manifolds," Biometrics, The International Biometric Society, vol. 77(4), pages 1328-1341, December.
    14. Gouriéroux, Christian & Monfort, Alain & Zakoian, Jean-Michel, 2017. "Pseudo-Maximum Likelihood and Lie Groups of Linear Transformations," MPRA Paper 79623, University Library of Munich, Germany.
    15. C. Gouriéroux & A. Monfort & J.‐M. Zakoïan, 2019. "Consistent Pseudo‐Maximum Likelihood Estimators and Groups of Transformations," Econometrica, Econometric Society, vol. 87(1), pages 327-345, January.
    16. Prado, Raquel & Molina, Francisco & Huerta, Gabriel, 2006. "Multivariate time series modeling and classification via hierarchical VAR mixtures," Computational Statistics & Data Analysis, Elsevier, vol. 51(3), pages 1445-1462, December.
    17. Jane L. Harvill & Priya Kohli & Nalini Ravishanker, 2017. "Clustering Nonlinear, Nonstationary Time Series Using BSLEX," Methodology and Computing in Applied Probability, Springer, vol. 19(3), pages 935-955, September.
    18. Marios Sergides & Efstathios Paparoditis, 2009. "Frequency Domain Tests of Semiparametric Hypotheses for Locally Stationary Processes," Scandinavian Journal of Statistics, Danish Society for Theoretical Statistics;Finnish Statistical Society;Norwegian Statistical Association;Swedish Statistical Association, vol. 36(4), pages 800-821, December.
    19. Christoph Schleicher, 2002. "An Introduction to Wavelets for Economists," Staff Working Papers 02-3, Bank of Canada.
    20. Luís Aguiar-Conraria & Maria Soares, 2011. "Oil and the macroeconomy: using wavelets to analyze old issues," Empirical Economics, Springer, vol. 40(3), pages 645-655, May.

    More about this item

    Keywords

    Nonlinear wavelet thresholding ; non-Euclidean geometry ; sample covariance matrices ; time-varying second-order structure ; log-Wishart distribution;
    All these keywords.

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:aiz:louvad:2024004. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Nadja Peiffer (email available below). General contact details of provider: https://edirc.repec.org/data/isuclbe.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.