Inference for Non-Stationary Heavy Tailed Time Series
Statistics Theory
2024-07-09 v3 Statistics Theory
Abstract
We consider the problem of inference for non-stationary time series with heavy-tailed error distribution. Under a time-varying linear process framework we show that there exists a suitable local approximation by a stationary process with heavy-tails. This enable us to introduce a local approximation-based estimator which estimates consistently time-varying parameters of the model at hand. To develop a robust method, we also suggest a self-weighing scheme which is shown to recover the asymptotic normality of the estimator regardless of whether the finite variance of the underlying process exists. Empirical evidence favoring this approach is provided.
Keywords
Cite
@article{arxiv.2212.11253,
title = {Inference for Non-Stationary Heavy Tailed Time Series},
author = {Fumiya Akashi and Konstantinos Fokianos and Junichi Hirukawa},
journal= {arXiv preprint arXiv:2212.11253},
year = {2024}
}
Comments
44 pages, 3 figures and 9 tables