ABSTRACT
This introduction presents an overview of the key concepts discussed in the subsequent chapters of this book. The book focuses on geostatistical and areal data. It describes the principal effects of spatial autocorrelation on the statistical properties of data. The book discusses some of the common graphical methods for exploring spatial data. It addresses the incorporation of spatial effects into models for the relationship between a response variable and its environment through the use of mixed model theory. The book provides an introduction to Bayesian methods of spatial data analysis, which are rapidly gaining in popularity as their advantages become better exploited. It also describes methods for the explicit incorporation of spatial autocorrelation into the analysis of replicated experiments. Remote sensing permits data to be gathered over a wide area at relatively low cost, and the global positioning system permits locations to be easily determined on the surface of the earth with sub-meter accuracy.
