Premium
On spatial skew‐Gaussian processes and applications
Author(s) -
Zhang Hao,
ElShaarawi Abdel
Publication year - 2010
Publication title -
environmetrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.68
H-Index - 58
eISSN - 1099-095X
pISSN - 1180-4009
DOI - 10.1002/env.982
Subject(s) - skew , covariance function , covariance , inference , monte carlo method , marginal distribution , gaussian process , marginal likelihood , mathematics , statistics , likelihood function , statistical physics , computer science , gaussian , econometrics , maximum likelihood , random variable , artificial intelligence , physics , telecommunications , quantum mechanics
In many applications, observed spatial variables have skewed distributions. It is often of interest to model the shape of the skewed marginal distributions as well as the spatial correlations. We propose a class of stationary processes that have skewed marginal distributions. The covariance function of the process can be given explicitly. We study maximum likelihood inference through a Monte Carlo EM algorithm, and develop a method for the minimum mean‐square error prediction. We also present two applications of the process. Copyright © 2009 John Wiley & Sons, Ltd.