A0548
Title: Variogram models on all spheres
Authors: Juan Du - Kansas State University (United States) [presenting]
Abstract: Variogram or variogram matrix functions play an important role in modeling dependence structure among multiple processes at different locations in spatial statistics. With more and more data collected on a global scale in environmental science, climatology, geophysics, and related fields, we focus on the characterizations of the variogram models on spheres of all dimensions for both stationary and intrinsic stationary, univariate and multivariate processes. Some efficient approaches are proposed to construct a variety of variogram functions including simple polynomial structures, or to show whether an existing function on Euclidean space is valid on all spheres. In particular, the series representation and spherical behavior of intrinsic stationary random fields are elaborated in both theory and simulation study. We also use simulation and real data analysis to demonstrate the application of the proposed models and theoretical results involved in terms of estimation and kriging.
