Detecting multiple change-points in the mean of Gaussian process by model selection

Authors:
E. Lebarbier
Affiliations:
INA-PG (Dépt OMIP)/INRA (Dépt BIA), 16 rue Claude Bernard, 75231 Paris, Cedex 05, France
Venue:
Signal Processing
Year:
2005

Citing 3
Cited 9

Analysis of discrete ill-posed problems by means of the L-curve

SIAM Review
Detection of abrupt changes: theory and application

Detection of abrupt changes: theory and application
An application of MCMC methods for the multiple change-points problem

Signal Processing - Special section on Markov Chain Monte Carlo (MCMC) methods for signal processing

Data-driven neighborhood selection of a Gaussian field

Computational Statistics & Data Analysis
Joint segmentation of multivariate Gaussian processes using mixed linear models

Computational Statistics & Data Analysis
Segmentation of the mean of heteroscedastic data via cross-validation

Statistics and Computing
Slope heuristics: overview and implementation

Statistics and Computing
A new segmentation-clustering method to analyse feeding behaviour of ruminants from within-day cumulative intake patterns

Computers and Electronics in Agriculture
Exact posterior distributions and model selection criteria for multiple change-point detection problems

Statistics and Computing
Detecting changes in time series: A product partition model with across-cluster correlation

Signal Processing
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	0.10

Visualization

Abstract

This paper deals with the problem of detecting change-points in the mean of a signal corrupted by an additive Gaussian noise. The number of changes and their position are unknown. From a nonasymptotic point of view, we propose to estimate them with a method based on a penalized least-squares criterion. We choose the penalty function such that the resulting estimator minimizes the quadratic risk according to the results of Birgé and Massart. This penalty depends on unknown constants and we propose a calibration to obtain an automatic method. The performance of the method is assessed through simulation experiments. An application to real data is shown.