Changepoint Detection on a Graph of Time Series

  title={Changepoint Detection on a Graph of Time Series},
  author={Karl Lars Yvon Hallgren and Nicholas A. Heard and Melissa J. M. Turcotte},
  journal={Bayesian Analysis},
When analysing multiple time series that may be subject to changepoints, it is sometimes possible to specify a priori, by means of a graph G, which pairs of time series are likely to be impacted by simultaneous changepoints. This article proposes a novel Bayesian changepoint model for multiple time series that borrows strength across clusters of connected time series in G to detect weak signals for synchronous changepoints. The graphical changepoint model is further extended to allow dependence… 



Most Recent Changepoint Detection in Panel Data

This work presents a novel approach to detect sets of most recent changepoints in panel data that aims to pool information across time-series, so that it preferentially infer a most recently change at the same time-point in multiple series.

Bayesian detection of abnormal segments in multiple time series

A novel Bayesian approach to analysing multiple time-series with the aim of detecting abnormal regions, and demonstrates how it is possible to accurately and efficiently perform Bayesian inference, based upon recursions that enable independent sampling from the posterior distribution.

High-dimensional changepoint detection via a geometrically inspired mapping

It is demonstrated that if the input series is Gaussian, then the mappings preserve the Gaussianity of the data and this approach outperforms the current state-of-the-art multivariate changepoint methods in terms of accuracy of detected changepoints and computational efficiency.

Subset Multivariate Collective and Point Anomaly Detection

This work develops a test for a single collective anomaly that has power to simultaneously detect anomalies that are either rare, that is affecting few data sequences, or common and shows how to detect multiple anomalies in a way that is computationally efficient but avoids the approximations inherent in binary segmentation-like approaches.

Exact and efficient Bayesian inference for multiple changepoint problems

The method can cope with a range of models, and exact simulation from the posterior distribution is possible in a matter of minutes, and can be useful within an MCMC algorithm, even when the independence assumptions do not hold.

High dimensional change point estimation via sparse projection

A two‐stage procedure called inspect is proposed for estimation of the change points, arguing that a good projection direction can be obtained as the leading left singular vector of the matrix that solves a convex optimization problem derived from the cumulative sum transformation of the time series.

Malware Family Discovery Using Reversible Jump MCMC Sampling of Regimes

Here, reversible jump Markov chain Monte Carlo for change point detection is extended to incorporate regime-switching, allowing regimes to be inferred from malware instruction traces, leading to compelling performance results.

Reversible jump Markov chain Monte Carlo computation and Bayesian model determination

Markov chain Monte Carlo methods for Bayesian computation have until recently been restricted to problems where the joint distribution of all variables has a density with respect to some fixed

Spatial Statistics and Bayesian Computation

The early development of MCMC in Bayesian inference is traced, some recent computational progress in statistical physics is reviewed, based on the introduction of auxiliary variables, and its current and future relevance in Bayesesian applications are discussed.

Bayesian Methods for Nonlinear Classification and Regression

The “hint of quantum mechanics” via commuting operators reminded me that I never really understood my undergraduate course in quantum mechanics, and this is not a text from which to learn Bayesian methods.