Testing epidemic change in nearly nonstationary process with statistics based on residuals

DOI10.1007/S00362-015-0712-0MaRDI QIDQ1685200zbMATH OpenOpenAlexFDO

Authors Alfredas Račkauskas, Charles Suquet, Jurgita Markeviciute

Publication date 13 December 2017

Published in Statistical Papers (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1410.4945

zbMATH Keywords

Brownian motionregular variationautoregressive processepidemic changeuniform increments statistics

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Applications of statistics to biology and medical sciences; meta analysis (62P10)

Abstract: We study an epidemic type change in innovations of a first order autoregressive process $y_{n,k}=varph{i}_n{y}_{n,k-1}+epsilo{n}_k+a_{n,k}$, where $ph{i}_n$ is either a constant in $(-1,1)$ or a sequence in $(0,1)$, converging to 1. For $k$ inside some unknown interval $mathbb{I}_n^{a}st=(k^{a}st,k^{a}st+el{l}^{a}st]$, $a_{n,k}=a_n$ while $a_{n,k}=0$ for $k$ outside $mathbb{I}_n^{a}st$. When $a_{n}eq0$, we have an epidemic deviation from the usual (zero) mean of innovations. Since innovations are not observed, we build uniform increments statistics on residuals $(widehat{epsilon}_k)$ of the process $y_{n,k}$. We assume that innovations $(epsilo{n}_k)$ are regularly varying with index $pge2$ or satisfies integrability condition $li{m}_{toinfty}{t}^{p}P(|epsilo{n}_1|>t)=0$ for $p>2$ and $Eepsilo{n}_k^2<infty$ for $p=2$. We find the limit distributions of the tests under no change and prove consistency under short epidemics that is $$ for some $$.

Recommendations

• Epidemic change tests for the mean of innovations of an AR(1) process
• Testing the epidemic change in nearly nonstationary autoregressive processes
• Change in autoregressive processes
• Epidemic change-point detection in general causal time series
• Tests for change-points with epidemic alternatives

Cites work

• scientific article; zbMATH DE number 4013835 (Why is no real title available?)
• scientific article; zbMATH DE number 1026574 (Why is no real title available?)
• scientific article; zbMATH DE number 4000257 (Why is no real title available?)
• A General Approach to the Strong Law of Large Numbers
• Alternative boundaries for CUSUM tests
• CUSUM control schemes for Gaussian processes
• Detecting a Changed Segment in DNA Sequences
• Functional central limit theorems for sums of nearly nonstationary processes
• Hölder norm test statistics for epidemic change
• Inference about a change point in experimental neurophysiology
• Model selection by LASSO methods in a change-point model
• Necessary and sufficient condition for the functional central limit theorem in Hölder spaces
• Nonparametric monitoring of financial time series by jump-preserving control charts
• Testing for change-points with rank and sign statistics
• Testing the epidemic change in nearly nonstationary autoregressive processes
• The limit distribution of the maximum increment of a random walk with regularly varying jump size distribution
• Uniform Limit Theory for Stationary Autoregression

Cited in

(8)

• Epidemic change tests for the mean of innovations of an AR(1) process
• Guaranteed testing for epidemic changes of a linear regression model
• Testing for epidemic changes in the mean of a multiparameter stochastic process
• Tests for an Epidemic Change in a Sequence of Exponentially Distributed Random Variables
• Functional limit theorems in Hölder space for residuals of nearly nonstationary AR(1) process
• Testing the epidemic change in nearly nonstationary autoregressive processes
• Epidemic change-point detection in general causal time series
• Change detection in \(\mathrm{INAR}(p)\) processes against various alternative hypotheses

This page was built for publication: Testing epidemic change in nearly nonstationary process with statistics based on residuals

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1685200)