Skip to main navigation Skip to search Skip to main content

Using penalized contrasts for the change-point problem

  • Marc Lavielle
  • Université Paris-Saclay

Research output: Contribution to journal › Article › peer-review

534 Citations (Scopus)

Abstract

A methodology for model selection based on a penalized contrast is developed. This methodology is applied to the change-point problem, for estimating the number of change points and their location. We aim to complete previous asymptotic results by constructing algorithms that can be used in diverse practical situations. First, we propose an adaptive choice of the penalty function for automatically estimating the dimension of the model, i.e., the number of change points. In a Bayesian framework, we define the posterior distribution of the change-point sequence as a function of the penalized contrast. MCMC procedures are available for sampling this posterior distribution. The parameters of this distribution are estimated with a stochastic version of EM algorithm (SAEM). An application to EEG analysis and some Monte-Carlo experiments illustrate these algorithms.

Original languageEnglish
Pages (from-to)1501-1510
Number of pages10
JournalSignal Processing
Volume85
Issue number8
DOIs
Publication statusPublished - 1 Aug 2005
Externally publishedYes

Keywords

  • Change-point problem
  • Model selection
  • SAEM algorithm

Fingerprint

Dive into the research topics of 'Using penalized contrasts for the change-point problem'. Together they form a unique fingerprint.

Cite this