Fixed-domain asymptotics for a subclass of Mat\'{e}rn-type Gaussian random fields
Statistics Theory
2007-06-13 v1 Statistics Theory
Abstract
Stein [Statist. Sci. 4 (1989) 432--433] proposed the Mat\'{e}rn-type Gaussian random fields as a very flexible class of models for computer experiments. This article considers a subclass of these models that are exactly once mean square differentiable. In particular, the likelihood function is determined in closed form, and under mild conditions the sieve maximum likelihood estimators for the parameters of the covariance function are shown to be weakly consistent with respect to fixed-domain asymptotics.
Cite
@article{arxiv.math/0602302,
title = {Fixed-domain asymptotics for a subclass of Mat\'{e}rn-type Gaussian random fields},
author = {Wei-Liem Loh},
journal= {arXiv preprint arXiv:math/0602302},
year = {2007}
}
Comments
Published at http://dx.doi.org/10.1214/009053605000000516 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)