English

Estimating $\beta$-mixing coefficients

Machine Learning 2022-03-18 v1 Machine Learning Probability

Abstract

The literature on statistical learning for time series assumes the asymptotic independence or ``mixing' of the data-generating process. These mixing assumptions are never tested, nor are there methods for estimating mixing rates from data. We give an estimator for the β\beta-mixing rate based on a single stationary sample path and show it is L1L_1-risk consistent.

Keywords

Cite

@article{arxiv.1103.0941,
  title  = {Estimating $\beta$-mixing coefficients},
  author = {Daniel J. McDonald and Cosma Rohilla Shalizi and Mark Schervish},
  journal= {arXiv preprint arXiv:1103.0941},
  year   = {2022}
}

Comments

9 pages, accepted by AIStats. CMU Statistics Technical Report

R2 v1 2026-06-21T17:35:17.964Z