Exact posterior distributions and model selection criteria for multiple change-point detection problems

Authors:
G. Rigaill;E. Lebarbier;S. Robin
Affiliations:
AgroParisTech, UMR 518, Paris, France 75005 and INRA, UMR 518, Paris, France 75005 and Département de Transfert, Institut Curie, Paris, France 75005 and Bioinformatics and Statistics, NKI-AVL ...;AgroParisTech, UMR 518, Paris, France 75005 and INRA, UMR 518, Paris, France 75005;AgroParisTech, UMR 518, Paris, France 75005 and INRA, UMR 518, Paris, France 75005
Venue:
Statistics and Computing
Year:
2012

Citing 5
Cited 2

Assessing a Mixture Model for Clustering with the Integrated Completed Likelihood

IEEE Transactions on Pattern Analysis and Machine Intelligence
Detecting multiple change-points in the mean of Gaussian process by model selection

Signal Processing
Using penalized contrasts for the change-point problem

Signal Processing
Bayesian model choice based on Monte Carlo estimates of posterior model probabilities

Computational Statistics & Data Analysis
A comparison of estimators for regression models with change points

Statistics and Computing

Fast estimation of the Integrated Completed Likelihood criterion for change-point detection problems with applications to Next-Generation Sequencing data

Signal Processing
Exploring the latent segmentation space for the assessment of multiple change-point models

Computational Statistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In segmentation problems, inference on change-point position and model selection are two difficult issues due to the discrete nature of change-points. In a Bayesian context, we derive exact, explicit and tractable formulae for the posterior distribution of variables such as the number of change-points or their positions. We also demonstrate that several classical Bayesian model selection criteria can be computed exactly. All these results are based on an efficient strategy to explore the whole segmentation space, which is very large. We illustrate our methodology on both simulated data and a comparative genomic hybridization profile.