A0946
Title: Matrix-free conditional simulations of Gaussian random fields
Authors: Somak Dutta - Iowa State University (United States) [presenting]
Debashis Mondal - Washington University in St Louis (United States)
Abstract: In spatial analysis, conditional simulation of spatial variables at unobserved locations given the data at the observed location facilitates various statistical inferences but suffers from computational scalability when the sample size is large. The aim is to develop a matrix-free method for conditional simulation based on novel mathematical decompositions of the inverse-covariance matrix. The method applies to a broad class of spatial models, including the Gaussian Markov random fields, fractional Gaussian fields, and the Matern models. A practical application is described to mapping groundwater arsenic exceedance regions.
