Saved in:
Bibliographic Details
Main Authors: Badreau, Marie, Proïa, Frédéric
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.13444
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917681347690496
author Badreau, Marie
Proïa, Frédéric
author_facet Badreau, Marie
Proïa, Frédéric
contents This paper deals with unit root issues in time series analysis. It has been known for a long time that unit root tests may be flawed when a series although stationary has a root close to unity. That motivated recent papers dedicated to autoregressive processes where the bridge between stability and instability is expressed by means of time-varying coefficients. The process we consider has a companion matrix $A_{n}$ with spectral radius $ρ(A_{n}) < 1$ satisfying $ρ(A_{n}) \rightarrow 1$, a situation described as `nearly-unstable'. The question we investigate is: given an observed path supposed to come from a nearly-unstable process, is it possible to test for the `extent of instability', i.e. to test how close we are to the unit root? In this regard, we develop a strategy to evaluate $α$ and to test for $\mathcal{H}_0 : ``α= α_0"$ against $\mathcal{H}_1 : ``α> α_0"$ when $ρ(A_{n})$ lies in an inner $O(n^{-α})$-neighborhood of the unity, for some $0 < α< 1$. Empirical evidence is given about the advantages of the flexibility induced by such a procedure compared to the common unit root tests. We also build a symmetric procedure for the usually left out situation where the dominant root lies around $-1$.
format Preprint
id arxiv_https___arxiv_org_abs_2310_13444
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Testing for the extent of instability in nearly unstable processes
Badreau, Marie
Proïa, Frédéric
Statistics Theory
Methodology
This paper deals with unit root issues in time series analysis. It has been known for a long time that unit root tests may be flawed when a series although stationary has a root close to unity. That motivated recent papers dedicated to autoregressive processes where the bridge between stability and instability is expressed by means of time-varying coefficients. The process we consider has a companion matrix $A_{n}$ with spectral radius $ρ(A_{n}) < 1$ satisfying $ρ(A_{n}) \rightarrow 1$, a situation described as `nearly-unstable'. The question we investigate is: given an observed path supposed to come from a nearly-unstable process, is it possible to test for the `extent of instability', i.e. to test how close we are to the unit root? In this regard, we develop a strategy to evaluate $α$ and to test for $\mathcal{H}_0 : ``α= α_0"$ against $\mathcal{H}_1 : ``α> α_0"$ when $ρ(A_{n})$ lies in an inner $O(n^{-α})$-neighborhood of the unity, for some $0 < α< 1$. Empirical evidence is given about the advantages of the flexibility induced by such a procedure compared to the common unit root tests. We also build a symmetric procedure for the usually left out situation where the dominant root lies around $-1$.
title Testing for the extent of instability in nearly unstable processes
topic Statistics Theory
Methodology
url https://arxiv.org/abs/2310.13444