Advances and Applications in Statistics
Volume 25, Issue 1, Pages 15 - 29
(November 2011)
|
|
AIC, BIC AND EDC CRITERIA FOR HIGHER ORDER MARKOV CHAIN WITH DENUMERABLE STATE SPACE
Chang C. Y. Dorea, Jaques S. Lopes and Ary V. Medino
|
Abstract: Several alternatives to nested hypotheses testing techniques have been proposed in the framework of model selection. The best known are the AIC entropy-based information criterion. In this paper, we address the problem of estimating the order of a Markov chain with denumerable state space. It is shown that the EDC (efficient determination criterion), that encompass both AIC and BIC estimates, is a strongly consistent estimator of the true order. |
Keywords and phrases: AIC, BIC, EDC, Markov chain order, penalty term. |
|
Number of Downloads: 363 | Number of Views: 979 |
|