English

Wavelet eigenvalue regression in high dimensions

Statistics Theory 2022-08-01 v2 Statistics Theory

Abstract

In this paper, we construct the wavelet eigenvalue regression methodology in high dimensions. We assume that possibly non-Gaussian, finite-variance pp-variate measurements are made of a low-dimensional rr-variate (rpr \ll p) fractional stochastic process with non-canonical scaling coordinates and in the presence of additive high-dimensional noise. The measurements are correlated both time-wise and between rows. Building upon the asymptotic and large scale properties of wavelet random matrices in high dimensions, the wavelet eigenvalue regression is shown to be consistent and, under additional assumptions, asymptotically Gaussian in the estimation of the fractal structure of the system. We further construct a consistent estimator of the effective dimension rr of the system that significantly increases the robustness of the methodology. The estimation performance over finite samples is studied by means of simulations.

Keywords

Cite

@article{arxiv.2108.03770,
  title  = {Wavelet eigenvalue regression in high dimensions},
  author = {Patrice Abry and B. Cooper Boniece and Gustavo Didier and Herwig Wendt},
  journal= {arXiv preprint arXiv:2108.03770},
  year   = {2022}
}

Comments

33 pages, 3 figures. Minor revision. Companion to arXiv:2102.05761

R2 v1 2026-06-24T04:55:58.332Z