Abstract
Let \(\{X_n: n\in {{\mathbb {N}}}\}\) be a linear process with density function \(f(x)\in L^2({{\mathbb {R}}})\). We study wavelet density estimation of f(x). Under some regular conditions on the characteristic function of innovations, we achieve, based on the number of nonzero coefficients in the linear process, the minimax optimal convergence rate of the integrated mean squared error of density estimation. Considered wavelets have compact support and are twice continuously differentiable. The number of vanishing moments of mother wavelet is proportional to the number of nonzero coefficients in the linear process and to the rate of decay of characteristic function of innovations. Theoretical results are illustrated by simulation studies with innovations following Gaussian, Cauchy and chi-squared distributions.
Similar content being viewed by others
References
Baernstein A (2019) Symmetrization in analysis, with David Drasin and Richard S. Laugesen. New Mathematical Monographs, 36. Cambridge University Press, Cambridge
Bailey WN (1935) General hypergeometric series. Cambridge tracts in mathematics and mathematical physics
Badaoui M, Rhomari N (2015) Blockshrink wavelet density estimator in \(\phi \)-mixing framework, Functional Statistics and Applications. Springer, Berlin, pp 29–50
Chesneau C (2012) Wavelet linear estimation of a density and its derivatives from observations of mixtures under quadrant dependence. ProbStat Forum 5:38–46
Chesneau C (2014) A general result on the mean integrated squared error of the hard thresholding wavelet estimator under \(\alpha \)-mixing dependence. J Probab Stat, Article ID: 403764
Chesneau C, Dewan I, Doosti H (2012) Wavelet linear density estimation for associated stratified size-biased sample. J Nonparametric Stat 24(2):429–45
Chesneau C, Doosti H, Stone L (2019) Adaptive wavelet estimation of a function from an \(m\)-dependent process with possibly unbounded \(m\). Commun Stat - Theory Methods 48:1123–1135
Daubechies I (1992) Ten lectures on wavelets. Springer, New York
Donoho DL, Johnstone IM (1994) Ideal spatial adaptation by wavelet shrinkage. Biometrika 81:425–455
Donoho DL, Johnstone IM (1995) Adapting to unknown smoothness via wavelet shrinkage. J Am Stat Assoc 90:1200–1224
Donoho DL, Johnstone IM, Kerkyacharian G, Picard D (1995) Wavelet shrinkage: asymptopia? J R Stat Soc B 57:301–369
Donoho DL, Johnstone IM, Kerkyacharian G, Picard D (1996) Density estimation by wavelet thresholding. Ann Stat 24:508–539
Faÿ G, Moulines E, Roueff F, Taqqu MS (2009) Estimators of long-memory: Fourier versus wavelets. J Econom 151:159–177
Folland G (1999) Real analysis: modern techniques and their applications. Wiley, New York
Gannaz I, Wintenberger O (2010) Adaptive density estimation with dependent observations. ESAIM Probab Stat 14:151–172
Gauss F (1866) Disquisitiones generales circa sericm infinitam, Ges. Werke, 3, 123–163 and 207–229
Giné E, Madych WR (2014) On wavelet projection kernels and the integrated squared error in density estimation. Stat Probab Lett 91:32–40
Giraitis L, Koul HL, Surgailis D (1996) Asymptotic normality of regression estimators with long memory errors. Stat Probab Lett 29:317–335
Hall P, Hart JD (1990) Convergence rates in density estimation for data from infinite-order moving average processes. Probab Theory Relat Fields 87:253–274
Johnstone IM (1999) Wavelets and the theory of non-parametric function estimation. Philos Trans R Soc Lond Ser A: Math Phys Eng Sci 357(1760):2475–2493
Kou JK, Guo HJ (2018) Wavelet density estimation for mixing and size-biased data. J Inequalities Appl, p 189
Leblanc F (1996) Wavelet linear density estimator for a discrete time stochastic process: Lp-losses. Stat Probab Lett 27:71–84
Li L, Zhang B (2022) Nonlinear wavelet-based estimation to spectral density for stationary non-Gaussian linear processes. Appl Comput Harmon Anal 60:176–204
Lu L (2013) On the integrated squared error of the linear wavelet density estimator. J Stat Plan Inference 143:1548–1565
Lukacs E (1970) Characteristic functions, 2nd edn. Griffin & Co., London
Marron JS (1994) Visual understanding of higher order kernels. J Comput Graph Stat 3:447–458
Meloche J (1990) Asymptotic behavior of the mean integrated squared error of kernel density estimators for dependent observations. Can J Statistics 18(3):205–211
Mielniczuk J (1997) On the asymptotic mean integrated squared error of a kernel density estimator for dependent data. Stat Probab Lett 34:53–58
Priestley MB (1981) Spectral analysis and time series. Academic Press, New York
Saavedra A, Cao R (2000) On the estimation of the marginal density of a moving average process. Can J Stat 28(4):799–815
Samorodnitsky G, Taqqu MS (1994) Stable non-Gaussian random processes. Chapman and Hall, New York
Sang H, Sang Y (2017) Memory properties of transformations of linear processes. Stat. Inference Stoch. Process. 20:79–103
Sang H, Sang Y, Xu F (2018) Kernel entropy estimation for linear processes. J Time Ser Anal 39(4):563–591
Stein E, Shakarchi R (2003) Complex analysis. Princeton University Press, Princeton
Wahba G (1975) Optimal convergence properties of variable knot, kernel and orthogonal series methods for density estimation. Annu Stat 3:15–29
Wu WB, Mielniczuk J (2002) Kernel density estimation for linear processes. Annu Stat 30(5):1441–1459
Zhang S, Zheng Z (1999) On the asymptotic normality for the \(L_2\)-error of wavelet density estimators with application. Commun Stat - Theory Methods 28:1093–1104
Zygmund A (1966) Trigonometric series, vol I, II. Cambridge University Press, Cambridge
Acknowledgements
We thank Johannes Schmidt-Hieber and Fangjun Xu for many helpful comments. We are also grateful to the reviewers for numerous constructive remarks and comments that helped to improve the manuscript. The research of Aleksandr Beknazaryan and Peter Adamic is partially supported by the Natural Sciences and Engineering Research Council of Canada under Grant RGPIN-2017-05595. The research of Hailin Sang is partially supported by the Simons Foundation Grant 586789, USA.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Beknazaryan, A., Sang, H. & Adamic, P. On the integrated mean squared error of wavelet density estimation for linear processes. Stat Inference Stoch Process 26, 235–254 (2023). https://doi.org/10.1007/s11203-022-09281-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11203-022-09281-9