A Computationally Efficient, High-Dimensional Multiple Changepoint Procedure with Application to Global Terrorism Incidence

Tickle, Sam; Eckley, Idris A.; Fearnhead, Paul

doi:10.1111/rssa.12695

Cited by 6 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example Mei (2010) propose online monitoring multiple data streams by calculating statistics for a change for each individual data stream and then combining this information. There is an extensive literature on how one can combine such information in an efficient way (for example Cho and Fryzlewicz, 2015;Enikeeva and Harchaoui, 2019;Tickle et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

A Constant-per-Iteration Likelihood Ratio Test for Online Changepoint Detection for Exponential Family Models

Ward¹,

Romano²,

Eckley³

et al. 2023

Preprint

View full text Add to dashboard Cite

Online changepoint detection algorithms that are based on likelihood-ratio tests have been shown to have excellent statistical properties. However, a simple online implementation is computationally infeasible as, at time T , it involves considering O(T ) possible locations for the change. Recently, the FOCuS algorithm has been introduced for detecting changes in mean in Gaussian data that decreases the per-iteration cost to O(log T ). This is possible by using pruning ideas, which reduce the set of changepoint locations that need to be considered at time T to approximately log T . We show that if one wishes to perform the likelihood ratio test for a different one-parameter exponential family model, then exactly the same pruning rule can be used, and again one need only consider approximately log T locations at iteration T . Furthermore, we show how we can adaptively perform the maximisation step of the algorithm so that we need only maximise the test statistic over a small subset of these possible locations. Empirical results show that the resulting online algorithm, which can detect changes under a wide range of models, has a constant-per-iteration cost on average.

show abstract

Section: Discussionmentioning

confidence: 99%

A Constant-per-Iteration Likelihood Ratio Test for Online Changepoint Detection for Exponential Family Models

Ward¹,

Romano²,

Eckley³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…this point is discussed later in Section 6 of Tickle et al (2021), where it reports that among the very few detected changes, one corresponds to a change of data collection in January of 1998, when it started the practice of only including events retrospectively confirmed by two groups studying terrorism with the proviso that such events must meet at least five of six pre-set criteria. This is a great example of how the known data histories helped to provide a more reasonable interpretation of the analysis results, and I am glad to see that this information was available to the authors and subsequently to all of us.…”

Section: Minding Data Historiesmentioning

confidence: 99%

“…A vivid example of needing deeper data minding is provided by Tickle et al’s (2021) study on detecting changes in temporal trends for global terrorism events. Time trend analyses are particularly vulnerable to changes in data collection protocols or other confounding changes over time.…”

Section: Minding Data Historiesmentioning

confidence: 99%

Enhancing (Publications on) Data Quality: Deeper Data Minding and Fuller Data Confession

Meng

2021

Journal of the Royal Statistical Society Series A: Statistics in Society

View full text Add to dashboard Cite

Statistics typically treats data as inputs for analysis, whereas the broader data science enterprise deals with the entire data life cycle, including the phases that output data. This commentary argues that it would benefit statistics and (data) science if we statisticians were also to treat data as products in and of themselves, and accordingly subject them to data minding, a stringent quality inspection process that scrutinizes data conceptualization, data pre-processing, data curation and data provenance, in addition to data collection, the traditional objective of our emphasis before data analysis. A concrete step in promoting deeper data minding is to encourage fuller data confession in (statistical) publications, that is, to entice-or at least not to disincentivize-the authors into providing more details on the genealogy of a given body of data, including an account of its deliberations, especially with respect to sources of adverse influence on data quality. The collection of articles in this special issue (on data science for societies) provides both the inspiration and aspiration for deeper data minding and fuller data confession.

show abstract

“…The consistency of the approach proposed by Killick et al (2012) was subsequently established by Fisch et al (2019), who also show how pruning can be implemented when considering a minimal segment length. More recently, activity within the changepoint literature has focused on the multivariate sequence setting, either assuming changes occur contemporaneously (Grundy et al, 2020; Wang et al, 2019) or allowing changes to vary from one sequence to the next (Cho & Fryzlewicz, 2015; Hahn et al, 2020; Tickle et al, 2020; Wang & Samworth, 2018). The conditions in these settings require data to be observed across all sequences at the same time.…”

Section: Introductionmentioning

confidence: 99%

Detecting changes in mixed‐sampling rate data sequences

2022

View full text Add to dashboard Cite

Different environmental variables are often monitored using different sampling rates; examples include half‐hourly weather station measurements, daily CO2$$ {\mathrm{CO}}_2 $$ data, and six‐day satellite data. Further when researchers want to combine the data into a single analysis this often requires data aggregation or down‐scaling. When one is seeking to identify changes within multivariate data, the aggregation and/or down‐scaling processes obscure the changes we seek. In this article, we propose a novel changepoint detection algorithm which can analyze multiple time series for co‐occurring changepoints with potentially different sampling rates, without requiring preprocessing to a standard sampling scale. We demonstrate the algorithm on synthetic data before providing an example identifying simultaneous changes in multiple variables at a location on the Greenland ice sheet using synthetic aperture radar and weather station data.

show abstract

A Computationally Efficient, High-Dimensional Multiple Changepoint Procedure with Application to Global Terrorism Incidence

Abstract: This is an open access article under the terms of the Creat ive Commo ns Attri bution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Cited by 6 publications

References 41 publications

A Constant-per-Iteration Likelihood Ratio Test for Online Changepoint Detection for Exponential Family Models

A Constant-per-Iteration Likelihood Ratio Test for Online Changepoint Detection for Exponential Family Models

Enhancing (Publications on) Data Quality: Deeper Data Minding and Fuller Data Confession

Detecting changes in mixed‐sampling rate data sequences

Contact Info

Product

Resources

About