PARALLEL-PROCESSING OF SPATIAL STATISTICS

The computational intensity of spatial statistics, including measures of spatial association, has hindered their application to large empiri cal data sets. Computing environments using parallel processing have t he potential to eliminate this problem. In this paper, we develop a me thod for processing a computationally intensive measure of spatial ass ociation (G) in parallel and present the performance enhancements obta ined. Timing results are presented for a single processor and for 2-14 parallel processors operating on data sets containing 256-1600 point observations. The results indicate that significant improvements in pr ocessing time can be achieved using parallel architectures.