Hostname: page-component-7b7567c8c-7pwfn Total loading time: 0 Render date: 2026-11-15T20:33:36.445Z Has data issue: false hasContentIssue false
  • English
  • Français

Marcinkiewicz law of large numbers for outer products of heavy-tailed, long-range dependent data

Part of:Limit theoremsSequential methodsLinear inference, regression

Published online by Cambridge University Press:  10 June 2016

Michael A. Kouritzin and
Samira Sadeghi
Michael A. Kouritzin*
Affiliation:
University of Alberta
Samira Sadeghi*
Affiliation:
University of Alberta
*
* Postal address: Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton, AB T6G 2G1, Canada.
* Postal address: Department of Mathematical and Statistical Sciences, University of Alberta, Edmonton, AB T6G 2G1, Canada.
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

The Marcinkiewicz strong law, limn→∞(1 / n1/p)∑k=1n(Dk - D) = 0 almost surely with p ∈ (1, 2), is studied for outer products Dk = {XkX̅kT}, where {Xk} and {X̅k} are both two-sided (multivariate) linear processes (with coefficient matrices (Cl), (C̅l) and independent and identically distributed zero-mean innovations {Ξ} and {Ξ̅}). Matrix sequences Cl and C ̅l can decay slowly enough (as |l| → ∞) that {Xk,X ̅k} have long-range dependence, while {Dk} can have heavy tails. In particular, the heavy-tail and long-range-dependence phenomena for {Dk} are handled simultaneously and a new decoupling property is proved that shows the convergence rate is determined by the worst of the heavy tails or the long-range dependence, but not the combination. The main result is applied to obtain a Marcinkiewicz strong law of large numbers for stochastic approximation, nonlinear function forms, and autocovariances.

Keywords

Covariancelinear processMarcinkiewicz strong law of large numbersheavy tailslong-range dependencestochastic approximation

MSC classification

Primary:62J10: Analysis of variance and covariance62J12: Generalized linear models60F15: Strong theorems
Secondary:62L20: Stochastic approximation

Information

Type
Research Article
Information
Advances in Applied Probability , Volume 48 , Issue 2 , June 2016, pp. 349 - 368
Copyright
Copyright © Applied Probability Trust 2016 

References

[1]Avram, F. and Taqqu, M. S. (1987).Generalized powers of strongly dependent random variables.Ann. Prob. 15,767–775.Google Scholar
[2]Davis, R. and Resnick, S. (1986).Limit theory for the sample covariance and correlation functions of moving averages.Ann. Statist. 14,533–558.Google Scholar
[3]Dobrushin, R. L. and Major, P. (1979).Non-central limit theorems for nonlinear functionals of Gaussian fields.Z. Wahrscheinlichkeitsth. 50,27–52.Google Scholar
[4]Giraitis, and Surgailis, (1986).Multivariate Appell polynomials and the central limit theorem. In Dependence in Probability and Statistics,Birkhäuser,Boston, MA, pp.21–71.Google Scholar
[5]Giraitis, L. and Surgailis, D. (1990).A limit theorem for polynomials of linear process with long-range dependence.Lithuanian Math. J. 29,128–145.Google Scholar
[6]Horváth, L. and Kokoszka, P. (2008).Sample autocovariances of long-memory time series.Bernoulli 14,405–418.Google Scholar
[7]Karagiannis, T.,Molle, M. and Faloutsos, M. (2004).Long-range dependence ten years of Internet traffic modeling.IEEE Internet Comput. 8,57–64.Google Scholar
[8]Kouritzin, M. A. (1996).On the convergence of linear stochastic approximation procedures.IEEE Trans. Inform. Theory 42,1305–1309.CrossRefGoogle Scholar
[9]Kouritzin, M. A. (1996).On the interrelation of almost sure invariance principles for certain stochastic adaptive algorithms and for partial sums of random variables.J. Theoret. Prob. 9,811–840.Google Scholar
[10]Kouritzin, M. A. (1995).Strong approximation for cross-covariances of linear variables with long-range dependence.Stoch. Process. Appl. 60,343–353.Google Scholar
[11]Kouritzin, M. A. and Sadeghi, S. (2015).Convergence rates and decoupling in linear stochastic approximation algorithms.SIAM J. Control Optimization 53,1484–1508.Google Scholar
[12]Louhichi, S. and Soulier, P. (2000).Marcinkiewicz–Zygmund strong laws for infinite variance time series.Statist. Inference Stoch. Process. 3,31–40.Google Scholar
[13]Mandelbrot, B. (1972).Statistical methodology for non-periodic cycles: from the covariance to R/S analysis.Ann. Econ. Social Measurement 1,259–290.Google Scholar
[14]Mandelbrot, B. B. and Wallis, J. R. (1968).Noah, Joseph and operational hydrology.Water Resources Res. 4,909–918.Google Scholar
[15]Rosenblatt, M. (1961).Independence and dependence. In Proc. 4th Berkeley Symp. Math. Statist. Prob.,University of California Press,Berkeley, pp.431–443.Google Scholar
[16]Stout, W. F. (1974).Almost Sure Convergence.Academic Press,New York.Google Scholar
[17]Surgailis, D. (1982).Zones of attraction of self-similar multiple integrals.Lithuanian Math. J. 22,327–340.CrossRefGoogle Scholar
[18]Surgailis, D. (2004).Stable limits of sums of bounded functions of long-memory moving averages with finite variance.Bernoulli 10,327–355.CrossRefGoogle Scholar
[19]Taqqu, M. S. (1979).Convergence of integrated processes of arbitrary Hermite rank.Z. Wahrscheinlichkeitsth. 50,53–83.CrossRefGoogle Scholar
[20]Vaičiulis, M. (2003).Convergence of sums of Appell polynomials with infinite variance.Lithuanian Math. J. 43,67–82.Google Scholar
[21]Varotsos, C. and Kirk-Davidoff, D. (2006).Long-memory processes in ozone and temperature variations at the region 60 degrees S – 60 degrees N.Atmospheric Chemistry Phys. 6,4093–4100.Google Scholar
[22]Wu, W. B. and Min, W. (2005).On linear processes with dependent innovations.Stoch. Process. Appl. 115,939–958.Google Scholar
[23]Wu, W. B.,Huang, Y. and Zheng, W. (2010).Covariances estimation for long-memory processes.Adv. Appl. Prob. 42,137–157.CrossRefGoogle Scholar