Multiple change point detection and validation in autoregressive time series data

Lijing Ma, Andrew J. Grant, Georgy Sofronov

Research output: Contribution to journalConference paperpeer-review

3 Citations (Scopus)
11 Downloads (Pure)

Abstract

It is quite common that the structure of a time series changes abruptly. Identifying these change points and describing the model structure in the segments between these change points is of interest. In this paper, time series data is modelled assuming each segment is an autoregressive time series with possibly different autoregressive parameters. This is achieved using two main steps. The first step is to use a likelihood ratio scan based estimation technique to identify these potential change points to segment the time series. Once these potential change points are identified, modified parametric spectral discrimination tests are used to validate the proposed segments. A numerical study is conducted to demonstrate the performance of the proposed method across various scenarios and compared against other contemporary techniques.

Original languageEnglish
Pages (from-to)1507-1528
Number of pages22
JournalStatistical Papers
Volume61
Issue number4
Early online date13 Jul 2020
DOIs
Publication statusPublished - Aug 2020
EventWorkshop on Change Point Detection Limit Theorems, Algorithms, and Applications in Life Sciences - Greifswald, Germany
Duration: 8 Jul 201910 Jul 2019

Bibliographical note

Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

  • Changepoint detection
  • Autoregressive time series
  • Likelihood ratio scan statistics
  • Multiple testing problems

Fingerprint Dive into the research topics of 'Multiple change point detection and validation in autoregressive time series data'. Together they form a unique fingerprint.

Cite this