Optimal Penalty Term for EDC Markov Chain Order Estimator - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Annales de l'ISUP Année : 2008

Optimal Penalty Term for EDC Markov Chain Order Estimator

Résumé

The Efficient Détermination Criterion (EDC) generalizes the AIC and BIC criteria and provides a class of consistent estimators for the order of a Markov chain. Several authors hâve addressed the question of choosing between AIC or BIC estimâtes. The first tends to overestimate the order and the second, though consistent, may lead to underestimation. Ail these estimators are based on penalized maximum log-likelihood functions. In this work, we study the choice of the optimal penalty term and show that corresponds to neither AIC nor BIC estimators.
Fichier principal
Vignette du fichier
Pages de DEP_8-V-64396_(2008-2010)-13.pdf (2.93 Mo) Télécharger le fichier
Origine Accord explicite pour ce dépôt

Dates et versions

hal-03633210 , version 1 (06-04-2022)

Identifiants

  • HAL Id : hal-03633210 , version 1

Citer

Chang C. Y. Dorea. Optimal Penalty Term for EDC Markov Chain Order Estimator. Annales de l'ISUP, 2008, LII (3), pp.15-25. ⟨hal-03633210⟩

Collections

ANNALES-ISUP
24 Consultations
3041 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More