English

Records for the moving average of a time series

Statistical Mechanics 2021-01-19 v2 Mathematical Physics math.MP Probability

Abstract

We investigate how the statistics of extremes and records is affected when taking the moving average over a window of width pp of a sequence of independent, identically distributed random variables. An asymptotic analysis of the general case, corroborated by exact results for three distributions (exponential, uniform, power-law with unit exponent), evidences a very robust dichotomy, irrespective of the window width, between superexponential and subexponential distributions. For superexponential distributions the statistics of records is asymptotically unchanged by taking the moving average, up to interesting distribution-dependent corrections to scaling. For subexponential distributions the probability of record breaking at late times is increased by a universal factor RpR_p, depending only on the window width.

Keywords

Cite

@article{arxiv.1907.07598,
  title  = {Records for the moving average of a time series},
  author = {Claude Godrèche and Jean-Marc Luck},
  journal= {arXiv preprint arXiv:1907.07598},
  year   = {2021}
}

Comments

37 pages, 6 figures