English

Moments of Maximum: Segment of AR(1)

History and Overview 2019-08-13 v1 Statistics Theory Statistics Theory

Abstract

Let XtX_{t} denote a stationary first-order autoregressive process. Consider five contiguous observations (in time tt) of the series (e.g., X1,...,X5X_{1}, ..., X_{5}). Let MM denote the maximum of these. Let ρ\rho be the lag-one serial correlation, which satisfies ρ<1|\rho| < 1. For what value of ρ\rho is E(M)\mathbb{E}(M) maximized? How does V(M)\mathbb{V}(M) behave for increasing ρ\rho? Answers to these questions lie in Afonja (1972), suitably decoded.

Keywords

Cite

@article{arxiv.1908.04179,
  title  = {Moments of Maximum: Segment of AR(1)},
  author = {Steven Finch},
  journal= {arXiv preprint arXiv:1908.04179},
  year   = {2019}
}

Comments

14 pages, 2 figures