Climate regime shift detection with a trans‐dimensional, sequential Monte Carlo, variational Bayes method

DOI10.1111/ANZS.12265MaRDI QIDQ5229966zbMATH OpenOpenAlexFDO

Authors C. A. McGrory, Daniel Ahfock, Ricardo T. Lemos

Publication date 19 August 2019

Published in Australian <html_ent glyph="@amp;" ascii="&amp;"/> New Zealand Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1111/anzs.12265

zbMATH Keywords

sequential Monte Carlovariational Bayesclimate changePacific Decadal Oscillation (PDO) index

Mathematics Subject Classification ID

Markov processes: estimation; hidden Markov models (62M05) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Markov processes: hypothesis testing (62M02) Applications of statistics to environmental and related topics (62P12)

Recommendations

• Non-stationary time series clustering with application to climate systems
• Detecting regime transitions in time series using dynamic mode decomposition
• An exact approach to Bayesian sequential change point detection
• Analyzing state-dependent model-data comparison in multi-regime systems
• An MDL approach to the climate segmentation problem

Cites work

• A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains
• A sequential particle filter method for static models
• Finite mixture and Markov switching models.
• Importance sampling as a variational approximation
• Sequential Monte Carlo Methods in Practice
• Transdimensional sequential Monte Carlo using variational Bayes -- SMCVB
• Variational Bayesian analysis for hidden Markov models
• Variational approximations in Bayesian model selection for finite mixture distributions

This page was built for publication: Climate regime shift detection with a trans‐dimensional, sequential Monte Carlo, variational Bayes method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5229966)