1. Home
  2. Issues
  3. Volume 8, Issue 4 (2021)
  4. Modeling temporally uncorrelated compone ...

Modern Stochastics: Theory and Applications


Modeling temporally uncorrelated components of complex-valued stationary processes
Volume 8, Issue 4 (2021), pp. 475–508
Pub. online: 10 November 2021      Type: Research Article      Open accessOpen Access
Received
4 June 2021
Revised
6 October 2021
Accepted
6 October 2021
Published
10 November 2021

Abstract

A complex-valued linear mixture model is considered for discrete weakly stationary processes. Latent components of interest are recovered, which underwent a linear mixing. Asymptotic properties are studied of a classical unmixing estimator which is based on simultaneous diagonalization of the covariance matrix and an autocovariance matrix with lag τ. The main contributions are asymptotic results that can be applied to a large class of processes. In related literature, the processes are typically assumed to have weak correlations. This class is extended, and the unmixing estimator is considered under stronger dependency structures. In particular, the asymptotic behavior of the unmixing estimator is estimated for both long- and short-range dependent complex-valued processes. Consequently, this theory covers unmixing estimators that converge slower than the usual $\sqrt{T}$ and unmixing estimators that produce non-Gaussian asymptotic distributions. The presented methodology is a powerful preprocessing tool and highly applicable in several fields of statistics.

References

[1] 
Adali, T., Schreier, P.J.: Optimization and estimation of complex-valued signals: Theory and applications in filtering and blind source separation. IEEE Signal Process. Mag. 31(5), 112–128 (2014). MR1824645. https://doi.org/10.1109/78.847796
[2] 
Arcones, M.A.: Limit theorems for nonlinear functionals of a stationary Gaussian sequence of vectors. Ann. Probab. 22(4), 2242–2274 (1994). MR1331224
[3] 
Bai, S., Taqqu, M.: Multivariate limit theorems in the context of long-range dependence. J. Time Ser. Anal. 34(6), 717–743 (2013). MR3127215. https://doi.org/10.1111/jtsa.12046
[4] 
Bai, S., Taqqu, M.: Generalized Hermite processes, discrete chaos and limit theorems. Stoch. Process. Appl. 124(4), 1710–1739 (2014). MR3163219. https://doi.org/10.1016/j.spa.2013.12.011
[5] 
Beran, J.: Statistics for Long-Memory Processes. Chapman & Hall, New York (1994). MR1304490
[6] 
Beran, J., Feng, Y., Ghosh, S., Kulik, R.: Long-Memory Processes: Probabilistic Properties and Statistical Methods. Springer (2013). MR3075595. https://doi.org/10.1007/978-3-642-35512-7
[7] 
Billingsley, P.: Probability and Measure, Anniversary Edition. Wiley, Hoboken (2012). MR2893652
[8] 
Breuer, P., Major, P.: Central limit theorems for non-linear functionals of Gaussian fields. J. Multivar. Anal. 13(3), 425–441 (1983). MR0716933. https://doi.org/10.1016/0047-259X(83)90019-2
[9] 
Cichocki, A., Amari, S.-i.: Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications, vol. 1. John Wiley & Sons (2002)
[10] 
Comon, P., Jutten, C.: Handbook of Blind Source Separation: Independent Component Analysis and Applications. Academic Press (2010)
[11] 
Dobrushin, R.L., Major, P.: Non-central limit theorems for nonlinear functionals of Gaussian fields. Z. Wahrscheinlichkeitstheor. Verw. Geb. 50, 27–52 (1979). MR0550122. https://doi.org/10.1007/BF00535673
[12] 
Embrechts, P., Maejima, M.: Selfsimilar Processes. Princeton Series in Applied Mathematics, p. 111. Princeton University Press, Princeton, New Jersey (2002). MR1920153
[13] 
Eriksson, J., Ollila, E., Koivunen, V.: Essential statistics and tools for complex random variables. IEEE Trans. Signal Process. 58(10), 5400–5408 (2010). MR2722676. https://doi.org/10.1109/TSP.2010.2054085
[14] 
Fan, J., Wang, M., Yao, Q.: Modelling multivariate volatilities via conditionally uncorrelated components. J. R. Stat. Soc., Ser. B, Stat. Methodol. 70(4), 679–702 (2008). MR2523899. https://doi.org/10.1111/j.1467-9868.2008.00654.x
[15] 
Goodman, N.: Statistical analysis based on a certain multivariate complex Gaussian distribution (an introduction). Ann. Math. Stat. 34(1), 152–177 (1963). MR0145618. https://doi.org/10.1214/aoms/1177704250
[16] 
Ilmonen, P.: On asymptotic properties of the scatter matrix based estimates for complex valued independent component analysis. Stat. Probab. Lett. 83(4), 1219–1226 (2013). MR3041396. https://doi.org/10.1016/j.spl.2013.01.020
[17] 
Ilmonen, P., Oja, H., Serfling, R.: On invariant coordinate system (ICS) functionals. Int. Stat. Rev. 80(1), 93–110 (2012). MR2990347. https://doi.org/10.1111/j.1751-5823.2011.00163.x
[18] 
Leonenko, N.: Limit Theorems for Random Fields with Singular Spectrum, vol. 465. Springer (1999). MR1687092. https://doi.org/10.1007/978-94-011-4607-4
[19] 
Li, H., Correa, N.M., Rodriguez, P.A., Calhoun, V.D., Adali, T.: Application of independent component analysis with adaptive density model to complex-valued fMRI data. IEEE Trans. Biomed. Eng. 58(10), 2794–2803 (2011)
[20] 
Lietzén, N., Virta, J., Nordhausen, K., Ilmonen, P.: Minimum distance index for BSS, generalization, interpretation and asymptotics. Aust. J. Stat. 49(4), 57–68 (2020)
[21] 
Makogin, V., Spodarev, E.: Limit theorems for excursion sets of subordinated Gaussian random fields with long-range dependence. Stochastics, 1–32 (2021)
[22] 
Matteson, D.S., Tsay, R.S.: Dynamic orthogonal components for multivariate time series. J. Am. Stat. Assoc. 106(496), 1450–1463 (2011). MR2896848. https://doi.org/10.1198/jasa.2011.tm10616
[23] 
Miettinen, J., Nordhausen, K., Oja, H., Taskinen, S.: Statistical properties of a blind source separation estimator for stationary time series. Stat. Probab. Lett. 82(11), 1865–1873 (2012). MR2970285. https://doi.org/10.1016/j.spl.2012.06.025
[24] 
Miettinen, J., Illner, K., Nordhausen, K., Oja, H., Taskinen, S., Theis, F.J.: Separation of uncorrelated stationary time series using autocovariance matrices. J. Time Ser. Anal. 37(3), 337–354 (2016). MR3512961. https://doi.org/10.1111/jtsa.12159
[25] 
Miettinen, J., Matilainen, M., Nordhausen, K., Taskinen, S.: Extracting conditionally heteroskedastic components using independent component analysis. J. Time Ser. Anal. 41(2), 293–311 (2020). MR4086188. https://doi.org/10.1111/jtsa.12505
[26] 
Nordhausen, K., Oja, H., Tyler, D.E., et al.: Tools for exploring multivariate data: The package ICS. J. Stat. Softw. 28(6), 1–31 (2008)
[27] 
Nourdin, I., Peccati, G.: Stein’s method on Wiener chaos. Probab. Theory Relat. Fields 145(1), 75–118 (2009). MR2520122. https://doi.org/10.1007/s00440-008-0162-x
[28] 
Nourdin, I., Peccati, G.: Stein’s method and exact Berry-Esseen asymptotics for functionals of Gaussian fields. Ann. Probab. 37(6), 2231–2261 (2010). MR2573557. https://doi.org/10.1214/09-AOP461
[29] 
Nourdin, I., Peccati, G.: Normal Approximations Using Malliavin Calculus: From Stein’s Method to Universality. Cambridge University Press (2012). MR2962301. https://doi.org/10.1017/CBO9781139084659
[30] 
Nourdin, I., Peccati, G., Podolskij, M.: Quantitative Breuer–Major theorems. Stoch. Process. Appl. 121(4), 793–812 (2011). MR2770907. https://doi.org/10.1016/j.spa.2010.12.006
[31] 
Picinbono, B.: Second-order complex random vectors and normal distributions. IEEE Trans. Signal Process. 44(10), 2637–2640 (1996)
[32] 
R Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria (2018). R Foundation for Statistical Computing. https://www.R-project.org/
[33] 
Samorodnitsky, G.: Long range dependence. Found. Trends Stoch. Syst. 1(3), 163–257 (2007). MR2379935. https://doi.org/10.1561/0900000004
[34] 
Taqqu, M.: Weak convergence to fractional Brownian motion and to the Rosenblatt process. Probab. Theory Relat. Fields 31(4), 287–302 (1975). MR0400329. https://doi.org/10.1007/BF00532868
[35] 
Tong, L., Soon, V., Huang, Y.-F., Liu, R.: Amuse: a new blind identification algorithm. In: IEEE International Symposium on Circuits and Systems, pp. 1784–1787. IEEE (1990).
[36] 
Tudor, C.A.: Analysis of Variations for Self-similar Processes: A Stochastic Calculus Approach. Springer (2013). MR3112799. https://doi.org/10.1007/978-3-319-00936-0
[37] 
Urbanek, S.: Jpeg: Read and Write JPEG Images. (2014). R package version 0.1-8. https://CRAN.R-project.org/package=jpeg
[38] 
Van der Vaart, A.W.: Asymptotic Statistics, vol. 3. Cambridge University Press (2000). MR1652247. https://doi.org/10.1017/CBO9780511802256
[39] 
Viitasaari, L., Ilmonen, P.: On modeling a class of weakly stationary processes. Front. Appl. Math. Stat. 15 (2020).
[40] 
Wendler, M., Wu, W.B.: Central limit theorems for nearly long range dependent subordinated linear processes. J. Appl. Probab. 57(2), 637–656 (2020). MR4125469. https://doi.org/10.1017/jpr.2020.10
[41] 
Zarzoso, V., Comon, P.: Robust independent component analysis by iterative maximization of the kurtosis contrast with algebraic optimal step size. IEEE Trans. Neural Netw. 21(2), 248–261 (2009)

Full article Cited by PDF XML
Full article Cited by PDF XML

Copyright
© 2021 The Author(s). Published by VTeX
Open access article under the CC BY license.

Keywords
Asymptotic theory blind source separation long-range dependency multivariate analysis noncentral limit theorems

MSC2010
62H12 60F05 60G15 60G10 94A12 94A08

Funding
N. Lietzén gratefully acknowledges financial support from the Emil Aaltonen Foundation (Grant 180144 N) and from the Academy of Finland (Grant 321968).

Metrics
since March 2018
491

Article info
views

604

Full article
views

386

PDF
downloads

112

XML
downloads


Share


RSS