Home > Research > Publications & Outputs > Micro-Macro Changepoint Inference for Periodic ...

Electronic data

  • Multilevel_Changepoint_Inference_for_Periodic_Data_Sequences

    Rights statement: 12m

    Accepted author manuscript, 1.1 MB, PDF document

    Embargo ends: 1/01/50

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Micro-Macro Changepoint Inference for Periodic Data Sequences

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Forthcoming

Standard

Micro-Macro Changepoint Inference for Periodic Data Sequences. / Ushakova, Anastasia; Taylor, Simon; Killick, Rebecca.

In: Journal of Computational and Graphical Statistics, 01.07.2022.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Ushakova A, Taylor S, Killick R. Micro-Macro Changepoint Inference for Periodic Data Sequences. Journal of Computational and Graphical Statistics. 2022 Jul 1. doi: 10.1080/10618600.2022.2104288

Author

Ushakova, Anastasia ; Taylor, Simon ; Killick, Rebecca. / Micro-Macro Changepoint Inference for Periodic Data Sequences. In: Journal of Computational and Graphical Statistics. 2022.

Bibtex

@article{886e9f2a989745f79aff2d7a19b82154,
title = "Micro-Macro Changepoint Inference for Periodic Data Sequences",
abstract = "Existing changepoint approaches consider changepoints to occur linearly in time; one changepoint happens after another and they are not linked. However, data processes may have regularly occurring changepoints, e.g. a yearly increase in sales of ice-cream on the first hot weekend. Using linear changepoint approaches here will miss more global features such as a decrease in sales of ice-cream due to other product availability. Being able to tease these global changepoint features from the more local (periodic) ones is beneficial for inference. We propose a periodic changepoint model to model this behavior using a mixture of a periodic and linear time perspective. Built around a Reversible Jump Markov Chain Monte Carlo sampler, the Bayesian framework is used to study the local (periodic) changepoint behavior. To identify the optimal global changepoint positions we integrate the local changepoint model into the pruned exact linear time (PELT) search algorithm. We demonstrate that the method detects both local and global changepoints with high accuracy on simulated and motivating applications that share periodic behavior. Due to the micro-macro nature of the analysis, visualization of the results can be challenging. We additionally provide a unique perspective for changepoint visualizations in these data sequences. ",
keywords = "PELT, segmentation, periodicity, level shift, house price index, North Atlantic Oscillation",
author = "Anastasia Ushakova and Simon Taylor and Rebecca Killick",
year = "2022",
month = jul,
day = "1",
doi = "10.1080/10618600.2022.2104288",
language = "English",
journal = "Journal of Computational and Graphical Statistics",
issn = "1061-8600",
publisher = "American Statistical Association",

}

RIS

TY - JOUR

T1 - Micro-Macro Changepoint Inference for Periodic Data Sequences

AU - Ushakova, Anastasia

AU - Taylor, Simon

AU - Killick, Rebecca

PY - 2022/7/1

Y1 - 2022/7/1

N2 - Existing changepoint approaches consider changepoints to occur linearly in time; one changepoint happens after another and they are not linked. However, data processes may have regularly occurring changepoints, e.g. a yearly increase in sales of ice-cream on the first hot weekend. Using linear changepoint approaches here will miss more global features such as a decrease in sales of ice-cream due to other product availability. Being able to tease these global changepoint features from the more local (periodic) ones is beneficial for inference. We propose a periodic changepoint model to model this behavior using a mixture of a periodic and linear time perspective. Built around a Reversible Jump Markov Chain Monte Carlo sampler, the Bayesian framework is used to study the local (periodic) changepoint behavior. To identify the optimal global changepoint positions we integrate the local changepoint model into the pruned exact linear time (PELT) search algorithm. We demonstrate that the method detects both local and global changepoints with high accuracy on simulated and motivating applications that share periodic behavior. Due to the micro-macro nature of the analysis, visualization of the results can be challenging. We additionally provide a unique perspective for changepoint visualizations in these data sequences.

AB - Existing changepoint approaches consider changepoints to occur linearly in time; one changepoint happens after another and they are not linked. However, data processes may have regularly occurring changepoints, e.g. a yearly increase in sales of ice-cream on the first hot weekend. Using linear changepoint approaches here will miss more global features such as a decrease in sales of ice-cream due to other product availability. Being able to tease these global changepoint features from the more local (periodic) ones is beneficial for inference. We propose a periodic changepoint model to model this behavior using a mixture of a periodic and linear time perspective. Built around a Reversible Jump Markov Chain Monte Carlo sampler, the Bayesian framework is used to study the local (periodic) changepoint behavior. To identify the optimal global changepoint positions we integrate the local changepoint model into the pruned exact linear time (PELT) search algorithm. We demonstrate that the method detects both local and global changepoints with high accuracy on simulated and motivating applications that share periodic behavior. Due to the micro-macro nature of the analysis, visualization of the results can be challenging. We additionally provide a unique perspective for changepoint visualizations in these data sequences.

KW - PELT

KW - segmentation

KW - periodicity

KW - level shift

KW - house price index

KW - North Atlantic Oscillation

U2 - 10.1080/10618600.2022.2104288

DO - 10.1080/10618600.2022.2104288

M3 - Journal article

JO - Journal of Computational and Graphical Statistics

JF - Journal of Computational and Graphical Statistics

SN - 1061-8600

ER -