Bayesian Multiple Changepoint Detection for Stochastic Models in Continuous Time

Shaochuan, Lu

doi:10.1214/20-ba1218

Cited by 6 publications

(15 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It seems that deep seismicity was quiescent between 1955 and 1986 and active after 2007 until recently. The result is only slightly different from those in Lu (2021), as more data were collected in this analysis. We perform further analysis with conjugate prior

normalΓ false(12,6 false)

for

λ

.…”

Section: Simulation Studies and Real Data Analysiscontrasting

confidence: 85%

“…We propose an efficient Gibbs sampler, which is based on an auxiliary uniformisation forward‐filtering backward‐sampling (AU‐FFBS) algorithm to sample approximately from the posterior of the number of changepoints and their positions. The method is a new application of the existing methods in Lu (2021). It is noted that both the computational and storage costs in most existing forward‐backward recursions are quadratic to

n

.…”

Section: Model Formulation and The Uniformisationmentioning

confidence: 99%

“…This version of the FFBS algorithm is also suitable for real-time changepoint detection. It has been applied for the inference of changepoints in random processes; see Lu (2021). We consider applying this sparse filtering recursion for the inference of changepoints in discrete time.…”

Section: Sparse Filtering Recursions IImentioning

confidence: 99%

“…To enhance the efficiency of the algorithm, we consider three techniques: thinning, truncation and pruning; see Lu (2021).…”

Section: The Gibbs Samplermentioning

confidence: 99%

See 3 more Smart Citations

Scalable Bayesian Multiple Changepoint Detection via Auxiliary Uniformisation

Shaochuan

2022

Int Statistical Rev

View full text Add to dashboard Cite

Summary In this paper, we perform a sparse filtering recursion for efficient changepoint detection for discrete‐time observations. We attach auxiliary event times to the chronologically ordered observations and formulate multiple changepoint problems of discrete‐time observations into continuous‐time observations. Ideally, both the computational and memory costs of the proposed auxiliary uniformisation forward‐filtering backward‐sampling algorithm can be quadratically scaled down to the number of changepoints instead of the number of observations, which would otherwise be prohibitive for a long sequence of observations. To avoid model bias, a time‐varying changepoint recurrence rate across different segments is assumed to characterise diverse scales of run lengths of the changepoints. We demonstrate the methods through simulation studies and real data analysis.

show abstract

normalΓ false(12,6 false)

for

λ

.…”

Section: Simulation Studies and Real Data Analysiscontrasting

confidence: 85%

n

.…”

Section: Model Formulation and The Uniformisationmentioning

confidence: 99%

Section: Sparse Filtering Recursions IImentioning

confidence: 99%

“…To enhance the efficiency of the algorithm, we consider three techniques: thinning, truncation and pruning; see Lu (2021).…”

Section: The Gibbs Samplermentioning

confidence: 99%

See 2 more Smart Citations

Scalable Bayesian Multiple Changepoint Detection via Auxiliary Uniformisation

Shaochuan

2022

Int Statistical Rev

View full text Add to dashboard Cite

show abstract

“…It was clearly shown that exploiting the spatial properties of the event and the structure of the sensor network can significantly reduce the ADD of the parallel multiple change-point detection compared to procedures that ignore this information. A topic for future research is multiple change-point detection in continuous time [9,15,16].…”

Section: Discussionmentioning

confidence: 99%

Bayesian Multiple Change-Point Detection of Propagating Events

Halme

Nitzan

Koivunen

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Detection of multiple spatial events in parallel is of wide interest in many modern applications, such as Internet of Things, environmental monitoring, and wireless communication. Sensor networks can be used for acquiring data and performing inference. In this paper, we take a Bayesian approach and model the detection of spatial events as a Bayesian multiple change point detection problem. The sensor network is assumed to be divided into distinct known clusters. In each cluster, a point source generates a spatial event that propagates omnidirectionally. The event causes a change in the local environment, which changes the distribution of observations at sensors located within the realm of this event. We propose a method for performing sequential multiple change-point detection under the Bayesian paradigm. It is shown analytically that the proposed procedure controls the false discovery rate (FDR), which is an appropriate criterion for statistically controlling the prevalence of false alarms in a setting where multiple decisions are made in parallel. It is numerically shown that exploiting spatial information decreases the average detection delay compared to procedures that do not properly use this information.

show abstract

Bayesian multiple changepoint detection with missing data and its application to the magnitude‐frequency distributions

Shaochuan

2022

Environmetrics

View full text Add to dashboard Cite

The detection of abrupt changes in an evolving pattern of time series in the presence of missing data still poses a challenge to real applications. We formulate the multiple changepoint problem into a latent Markov model on a countably infinite state space. For efficiency-enhancing, we propose a partially collapsed Gibbs sampler for the inference of the joint posterior of the number of changepoints and their locations. Variants of Viterbi algorithms are suggested for obtaining the MAP estimates of random changepoints in the presence of missing data, which provides better performances in these varying-dimensional problems. The method is generally applicable for multiple changepoint detection under a variety of missing data mechanism. The method is applied to a case study of the magnitude-frequency distribution of the 2010 Darfield M7.1 earthquake sequence in New Zealand. We find out some unusual features of the seismic b-value in the Darfield earthquake sequence. It is noted that two changepoints are detected and in contrast to the background seismic b-value, relatively low b-values in the early aftershock propagation period are identified. We suggest that this might be a forewarning of potentially devastatingly strong aftershocks.The advance in the method of b-value changepoint detection will enhance our understanding of earthquake occurrence and potentially lead to improved risk forecasting.

show abstract

Bayesian Multiple Changepoint Detection for Stochastic Models in Continuous Time

Cited by 6 publications

References 32 publications

Scalable Bayesian Multiple Changepoint Detection via Auxiliary Uniformisation

Scalable Bayesian Multiple Changepoint Detection via Auxiliary Uniformisation

Bayesian Multiple Change-Point Detection of Propagating Events

Bayesian multiple changepoint detection with missing data and its application to the magnitude‐frequency distributions

Contact Info

Product

Resources

About