A comparison of single and multiple changepoint techniques for time series data

Xuesheng Shi, Colin Gallagher, Robert Lund and Rebecca Killick

Computational Statistics & Data Analysis, 2022, vol. 170, issue C

Abstract: Correlated time series data arise in many applications. This paper describes and compares several prominent single and multiple changepoint techniques for correlated time series. In the single changepoint problem, various cumulative sum (CUSUM) and likelihood ratio statistics, along with boundary cropping scenarios and scaling methods (e.g., scaling to an extreme value or Brownian Bridge limit) are compared. A recently developed test based on summing squared CUSUM statistics over all time indices is shown to have controlled Type I error and superior detection power. In the multiple changepoint setting, penalized likelihoods drive the discourse, with AIC, BIC, mBIC, and MDL penalties being considered. Binary and wild binary segmentation techniques are also compared. A new distance metric is introduced that measures differences between two multiple changepoint segmentations. Algorithmic and computational concerns are discussed and simulations are given to support all conclusions. In the end, the multiple changepoint setting admits no clear methodological winner, performance depending on the particular scenario. Nonetheless, some practical guidance emerges.

Keywords: AMOC techniques; ARMA models; Binary segmentation; Brownian bridge; CUSUM tests; Likelihood ratio test; Minimum description length; One-step-ahead prediction residuals; Penalized likelihoods; Wild binary segmentation (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0167947322000135
Full text for ScienceDirect subscribers only.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:csdana:v:170:y:2022:i:c:s0167947322000135

DOI: 10.1016/j.csda.2022.107433

Access Statistics for this article

Computational Statistics & Data Analysis is currently edited by S.P. Azen

More articles in Computational Statistics & Data Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().