Spatio-temporal processes

We present an overview of the literature on the analysis of spatio-temporal processes with a nonseparable covariance structure. We focus on those methods that rely heavily on computing for the estimation or inference. Topics are classified into frequentist approaches, which rely on expectation-maximization algorithms, and hierarchical Bayesian approaches, which rely on Markov chain Monte Carlo. We also present discussions on other computational issues related to the analysis of spatio-temporal data. (C) 2010 John Wiley & Sons, Inc.