Efficient Bayesian analysis of multiple changepoint models with dependence across segments
From MaRDI portal
Publication:692967
DOI10.1007/S11222-009-9163-6zbMATH Open1254.62029arXiv0910.3099OpenAlexW2056262371MaRDI QIDQ692967FDOQ692967
Authors: M. C. Fu 
Publication date: 6 December 2012
Published in: Statistics and Computing (Search for Journal in Brave)
Abstract: We consider Bayesian analysis of a class of multiple changepoint models. While there are a variety of efficient ways to analyse these models if the parameters associated with each segment are independent, there are few general approaches for models where the parameters are dependent. Under the assumption that the dependence is Markov, we propose an efficient online algorithm for sampling from an approximation to the posterior distribution of the number and position of the changepoints. In a simulation study, we show that the approximation introduced is negligible. We illustrate the power of our approach through fitting piecewise polynomial models to data, under a model which allows for either continuity or discontinuity of the underlying curve at each changepoint. This method is competitive with, or out-performs, other methods for inferring curves from noisy data; and uniquely it allows for inference of the locations of discontinuities in the underlying curve.
Full work available at URL: https://arxiv.org/abs/0910.3099
Recommendations
- Approximate simulation-free Bayesian inference for multiple changepoint models with dependence within segments
- Changepoint detection in non-exchangeable data
- A simple Bayesian approach to multiple change-points
- Estimation and comparison of multiple change-point models
- Adaptive MCMC for multiple changepoint analysis with applications to large datasets
Cites Work
- Gaussian Markov Random Fields
- Ideal spatial adaptation by wavelet shrinkage
- Rejection Control and Sequential Importance Sampling
- Bayesian forecasting and dynamic models
- Product partition models for change point problems
- Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion)
- Stochastic Volatility: Likelihood Inference and Comparison with ARCH Models
- Calculating posterior distributions and modal estimates in Markov mixture models
- Estimation and comparison of multiple change-point models
- Bayesian curve-fitting with free-knot splines
- Automatic Bayesian Curve Fitting
- Wavelet Thresholding via A Bayesian Approach
- An application of MCMC methods for the multiple change-points problem.
- Real Nonparametric Regression Using Complex Wavelets
- Detection and estimation for abruptly changing systems
- On-Line Inference for Hidden Markov Models via Particle Filters
- Bayesian Retrospective Multiple-Changepoint Identification
- The interacting multiple model algorithm for systems with Markovian switching coefficients
- Estimation of a noisy discrete-time step function: Bayes and empirical Bayes approaches
- Numerical Bayesian Methods Applied to Signal Processing
- Joint segmentation of wind speed and direction using a hierarchical model
- Posterior Probability Intervals for Wavelet Thresholding
- Bayesian analysis of isochores
- Exact Bayesian curve fitting and signal segmentation
Cited In (11)
- Changepoint detection in non-exchangeable data
- Detecting multiple random changepoints in Bayesian piecewise growth mixture models
- Adaptive MCMC for multiple changepoint analysis with applications to large datasets
- A consistent on‐line Bayesian procedure for detecting change points
- Approximate simulation-free Bayesian inference for multiple changepoint models with dependence within segments
- Exact Decoding of a Sequentially Markov Coalescent Model in Genetics
- Detecting Abrupt Changes in the Presence of Local Fluctuations and Autocorrelated Noise
- Multipartition model for multiple change point identification
- Scalable Bayesian Multiple Changepoint Detection via Auxiliary Uniformisation
- Simultaneous Credible Regions for Multiple Changepoint Locations
- Bayesian P-splines and advanced computing in R for a changepoint analysis on spatio-temporal point processes
Uses Software
This page was built for publication: Efficient Bayesian analysis of multiple changepoint models with dependence across segments
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q692967)
