A0427
Title: Classes of multivariate and space-time power-law covariance functions
Authors: Pulong Ma - Iowa State University (United States) [presenting]
Abstract: Understanding marginal covariance and cross-covariance structures is essential for modeling continuously indexed multivariate and space-time processes. The Matern covariance function, which only allows short-range dependence, has enabled several notable developments in multivariate and space-time covariance models in the past few decades. However, many geophysical processes possess long-range dependence in space and space-time domains, for which the Matern-based covariance models often fail to capture. To address this issue, new classes of multivariate and space-time covariance functions are introduced with power-law decay in the tail. Several validity conditions are derived to ensure the positive definiteness of the proposed multivariate covariance models. The interplay among long-range dependence, Markov property, and screening effect is examined theoretically to provide foundations for their practical usefulness. Extensive simulation examples and real datasets are used to illustrate the superior performance of the proposed covariance models over the state-of-the-art models.
