Let Y be a Markov random foeld on S parametrized via its local conditional specifications. We study consistency of coding and pseudo-likelihood estimators. Then we obtain conditional asymptotic normality for the coding estimator and deduce that the difference of coding statistic for two nested hypotheses is, unconditionally, a chi-square. For these results, we do not need regularity of the lattice, translation invariance for the specification or weak dependence for the field.
Publié le : 1992-07-05
Classification:
Conditional specification,
Markov random field,
coding and pseudo-likelihood estimators,
difference of coding tests,
62M02, 62M05,
[MATH.MATH-ST]Mathematics [math]/Statistics [math.ST]
@article{hal-00110636,
author = {Hardouin, C\'ecile and Guyon, Xavier},
title = {The chi-square coding test for nested Markov random field hypotheses},
journal = {HAL},
volume = {1992},
number = {0},
year = {1992},
language = {en},
url = {http://dml.mathdoc.fr/item/hal-00110636}
}
Hardouin, Cécile; Guyon, Xavier. The chi-square coding test for nested Markov random field hypotheses. HAL, Tome 1992 (1992) no. 0, . http://gdmltest.u-ga.fr/item/hal-00110636/