Retrospective multivariate Bayesian change-point analysis: A simultaneous single change in the mean of several hydrological sequences

Perreault, Luc; Parent, Éric; Bernier, Jacques; Bobée, Bernard; Slivitzky, Michel

doi:10.1007/s004770000051

Cited by 62 publications

(65 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Potential applications include the detection of distributed denial-of-service (DoS) attacks in computer networks (36), of weather and climate changes from meteorological data (37), and of disease outbreaks from surveillance data collected at multiple locations (38). These problems are similar to that of detecting conformational changes in biomolecules in that a distributed DoS attack, climate change, or disease outbreak is likely to cause a simultaneous change in a number of the monitored observables.…”

Section: Discussionmentioning

confidence: 99%

Identifying localized changes in large systems: Change-point detection for biomolecular simulations

Fan

Dror

Mildorf

et al. 2015

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

Research on change-point detection, the classical problem of detecting abrupt changes in sequential data, has focused predominantly on datasets with a single observable. A growing number of time series datasets, however, involve many observables, often with the property that a given change typically affects only a few of the observables. We introduce a general statistical method that, given many noisy observables, detects points in time at which various subsets of the observables exhibit simultaneous changes in data distribution and explicitly identifies those subsets. Our work is motivated by the problem of identifying the nature and timing of biologically interesting conformational changes that occur during atomic-level simulations of biomolecules such as proteins. This problem has proved challenging both because each such conformational change might involve only a small region of the molecule and because these changes are often subtle relative to the ever-present background of faster structural fluctuations. We show that our method is effective in detecting biologically interesting conformational changes in molecular dynamics simulations of both folded and unfolded proteins, even in cases where these changes are difficult to detect using alternative techniques. This method may also facilitate the detection of change points in other types of sequential data involving large numbers of observables-a problem likely to become increasingly important as such data continue to proliferate in a variety of application domains. molecular dynamics | conformational change | SIMPLE | penalized maximum likelihood | multivariate

show abstract

Section: Discussionmentioning

confidence: 99%

Identifying localized changes in large systems: Change-point detection for biomolecular simulations

Fan

Dror

Mildorf

et al. 2015

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

show abstract

“…For instance, there is evidence of such behavior in climatic and hydrological data series in the Africa Servat et al, 1997) and in the Pacific region (Kerr, 1992). As regards HydroQuébec energy inflow series, many annual runoff series for rivers situated in Northern Québec seem to exhibit this type of sudden drastic change (Perreault et al, 2000b). Thus, model (1) must be considered, at least as a first methodological step.…”

Section: Bayesian Analysis Of Normal Sequences With An Unknown Changementioning

confidence: 98%

Bayesian change-point analysis in hydrometeorological time series. Part 1. The normal model revisited

Perreault

Bernier

Bobée

et al. 2000

Journal of Hydrology

Self Cite

151

108

View full text Add to dashboard Cite

A Bayesian method is presented for the analysis of two types of sudden change at an unknown time-point in a sequence of energy inflows modeled by independent normal random variables. First, the case of a single shift in the mean level is revisited to show how such a problem can be straightforwardly addressed through the Bayesian framework. Second, a change in variability is investigated. In hydrology, to our knowledge, this problem has not been studied from a Bayesian perspective. Even if this model is quite simple, no analytic solutions for parameter inference are available, and recourse to approximations is needed. It is shown that the Gibbs sampler is particularly suitable for change-point analysis, and this Markovian updating scheme is used. Finally, a case study involving annual energy inflows of two large hydropower systems managed by Hydro-Québec is presented in which informative prior distributions are specified from regional information. ᭧

show abstract

“…The model probabilities assign equal weights to the "change" and "no change" alternatives [28], i.e., ( ) = 1/2 and ( ) = ( ) = 1/4 . , ( , ) is the Bayes factor of model , to model :…”

Section: Bayesian Model Selectionmentioning

confidence: 99%

Phenological Changes of Corn and Soybeans over U.S. by Bayesian Change-Point Model

Shen

Liu

2015

Sustainability

View full text Add to dashboard Cite

Abstract:In this paper, a Bayesian change-point model was used to examine the phenological changes in the predominant crop producing states of U.S over a 33-year period (1981-2013). Changes of phenological observation were categorized into a no-change model and two change models. The change point and intensity of shifts were subsequently estimated under the selected change model. The experiments were conducted in the cropping regions using the state-level crop progress reports issued by the U.S. Department of Agriculture. The results demonstrated that the planted, silking and mature stages of corn were significantly advanced under the change models; the vegetative period was shortened, and the reproductive and growing seasons were lengthened. The soybean phenological metrics followed a similar trend as that of corn, even though more states tended to change under a change model. The underlying drivers of such abrupt changes may be the confounding effects of crop breeding, agronomic management and climate change. Specific events, such as the adoption of genetically engineered crops in 1996-1997, can partly explain the changes in phenology. A comparison with the breakpoints function and Pettitt method demonstrated the feasibility and effectiveness of the Bayesian change-point model on crop phenological change detection.

show abstract

Retrospective multivariate Bayesian change-point analysis: A simultaneous single change in the mean of several hydrological sequences

Cited by 62 publications

References 14 publications

Identifying localized changes in large systems: Change-point detection for biomolecular simulations

Identifying localized changes in large systems: Change-point detection for biomolecular simulations

Bayesian change-point analysis in hydrometeorological time series. Part 1. The normal model revisited

Phenological Changes of Corn and Soybeans over U.S. by Bayesian Change-Point Model

Contact Info

Product

Resources

About