Mikyoung Jun
Texas A&M University

Covariance models for spatial data on a global scale

Global-scale geophysical, environmental, and climate science data sets require statistical models that reflect the curvature of their spatial domain. Mathematical limitations have prevented the use of the geodesic distance, the most natural metric for measuring distance on the surface of a sphere, and instead many previous approaches have applied the chordal distance to compute the covariance matrix. However, because these approximations may result in physically unrealistic distortions on the sphere, covariance functions directly defined on the sphere using the geodesic distance are needed. We discuss the issues that arise when dealing with global-scale spherical data. Some current approaches to building marginal and cross-covariance functions on the sphere will be discussed. Issues and some approaches for spatial point pattern data on a global scale will also be given.

Refreshments at 3:45pm in Snedecor 2101.