Cutoff for samples of Markov chains
Bernard Ycart (1999)
ESAIM: Probability and Statistics
Similarity:
Bernard Ycart (1999)
ESAIM: Probability and Statistics
Similarity:
Antoine Chambaz, Catherine Matias (2009)
ESAIM: Probability and Statistics
Similarity:
This paper deals with order identification for Markov chains with Markov regime (MCMR) in the context of finite alphabets. We define the joint order of a MCMR process in terms of the number of states of the hidden Markov chain and the memory of the conditional Markov chain. We study the properties of penalized maximum likelihood estimators for the unknown order of an observed MCMR process, relying on information theoretic arguments. The novelty of our work relies in the joint...
E. Nummelin, R. L. Tweedie (1976)
Annales scientifiques de l'Université de Clermont. Mathématiques
Similarity:
Galvin, David J. (2007)
Electronic Journal of Probability [electronic only]
Similarity:
Hans C. Andersen, Persi Diaconis (2007)
Journal de la société française de statistique
Similarity:
We present a generalization of hit and run algorithms for Markov chain Monte Carlo problems that is ‘equivalent’ to data augmentation and auxiliary variables. These algorithms contain the Gibbs sampler and Swendsen-Wang block spin dynamics as special cases. The unification allows theorems, examples, and heuristics developed in one domain to illuminate parallel domains.
Vigoda, Eric (2001)
The Electronic Journal of Combinatorics [electronic only]
Similarity:
Bressaud, Xavier, Fernández, Roberto, Galves, Antonio (1999)
Electronic Journal of Probability [electronic only]
Similarity:
Olivier Catoni (1999)
Séminaire de probabilités de Strasbourg
Similarity:
Bercu, Bernard, Del Moral, Pierre, Doucet, Arnaud (2009)
Electronic Journal of Probability [electronic only]
Similarity:
Mariusz Górajski (2009)
Annales UMCS, Mathematica
Similarity:
In this paper we consider an absorbing Markov chain with finite number of states. We focus especially on random walk on transient states. We present a graph reduction method and prove its validity. Using this method we build algorithms which allow us to determine the distribution of time to absorption, in particular we compute its moments and the probability of absorption. The main idea used in the proofs consists in observing a nondecreasing sequence of stopping times. Random walk on...
Kalashnikov, Vladimir V. (1994)
Journal of Applied Mathematics and Stochastic Analysis
Similarity: