Abstract
The problem of estimating the function when using a homogeneous linear operator in a model with correlated noise is considered. The asymptotic properties of estimating risk upon the threshold wavelet-vaguelette decomposition of a signal are studied. The conditions under which the asymptotic normality of an unbiased risk estimate holds are given.
Similar content being viewed by others
References
D. Donoho, “Nonlinear solution of linear inverse problems by wavelet-vaguelette decomposition,” Appl. Comput. Harmon. Anal. 2, 101–126 (1995).
D. Donoho and I. M. Johnstone, “Adapting to unknown smoothness via wavelet shrinkage,” J. Amer. Stat. Assoc. 90, 1200–1224 (1995).
D. Donoho and I. M. Johnstone, “Ideal spatial adaptation via wavelet shrinkage,” Biometrika 81, 425–455 (1994).
D. Donoho, I. M. Johnstone, G. Kerkyacharian, and D. Picard, “Wavelet shringage: asymoptopia?,” J. R. Statist. Soc. Ser. B, No. 2, 301–369 (1995).
N. Lee, PhD Thesis (Purdue Univ., West Lafayette, 1997).
J. S. Marron, S. Adak, I. M. Johnstone, M. H. Neumann, P. Patil, “Exact risk analysis of wavelet regression,” J. Comput. Graph. Stat. 7, 278–309 (1998).
A. V. Markin, “Limit distribution of risk assessment in the thresholding processing of wavelet coefficients,” Inform. Primen. 3(4), 57–63 (2009).
A. V. Markin and O. V. Shestakov, “Consistency of risk estimation with thresholding of wavelet coefficients,” Mos. Univ. Comput. Math. and Cybern. 34, 22–30 (2010).
A. V. Markin and O. V. Shestakov, “Asymptotics of risk estimation in threshold processing of wavelet-vaguelette coefficients in a tomography problem,” Inform. Primen. 4(2), 36–45 (2010).
O. V. Shestakov, “Approximation of the distribution estimated risk of threshold processing of wavelet coefficients by a normal distribution with the use of the sample variance,” Inform. Primen. 4(4), 73–81 (2010).
O. V. Shestakov, “On the accuracy of approximation of the distribution of estimated risk of threshold processing of wavelet coefficients of a signal by a normal distribution in the case of an unknown noise level,” Sist. Sredstva Inf. 22(1), 142–152 (2012).
O. V. Shestakov, “Asymptotic normality of adaptive wavelet thresholding risk estimation,” Dokl. Math. 86(1), 556–558 (2012).
O. V. Shestakov, “Dependence of the limit distribution of the estimated risk of threshold processing of wavelet coefficients of a signal on the type of the estimated variance of noise in selection of the adaptive threshold,” T-Comm.-Telekomm. Transport, No. 1, 46–51 (2012).
O. V. Shestakov, “Central limit theorem for the function of generalized cross-validation in threshold processing of wavelet coefficients,” Inform. Primen. 7(2), 40–49 (2013).
I. Daubechies, Ten Lectures on Wavelets (SIAM, Philadelphia, 1992; NITS RKHD, Izhevsk-Moscow, 2001).
S. Mallat, A Wavelet Tour of Signal Processing (Academic, New York, 1999).
A. Boggess and F. Narkowich, A First Course in Wavelets with Fourier Analysis (Prentice Hall, Upper Saddle River, 2001).
M. S. Taqqu, “Weak convergence to fractional Brownian motion and to the Rosenblatt process,” Z. Wahrscheinlichkeitsth. Verw. Geb. 31, 287–302 (1975).
I. M. Johnstone and B. W. Silverman, “Wavelet threshold estimates for data sith correlated noise,” J. R. Statist. Soc. Ser. B 59, 319–351 (1997).
I. M. Johnstone, “Wavelet shrinkage for correlated data and inverse problems: adaptivity results,” Statist. Sinica 9, 51–83 (1999).
E. D. Kolaczyk, PhD Thesis (Stanford Univ., Stanford, 1994).
R. C. Bradley, “Basic properties of strong mixing conditions. A survey and some open questions,” Probab. Surveys 2, 107–144 (2005).
M. Peligrad, “On the asymptotic normality of sequences of weak dependent random variables,” J. Theor. Probab. 9, 703–715 (1996).
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © A.A. Eroshenko, O.V. Shestakov, 2014, published in Vestnik Moskovskogo Universiteta. Vychislitel’naya Matematika i Kibernetika, 2014, No. 3, pp. 23–30.
About this article
Cite this article
Eroshenko, A.A., Shestakov, O.V. Asymptotic normality of estimating risk upon the wavelet-vaguelette decomposition of a signal function in a model with correlated noise. MoscowUniv.Comput.Math.Cybern. 38, 110–117 (2014). https://doi.org/10.3103/S0278641914030042
Received:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0278641914030042