Geostatistics: Past, Present, and Future

Geostatistical analyses were first developed in the 1950's as a result of interest in areal or block averages for ore reserves in the mining industry. Today, variogram estimation and spatial prediction (kriging) span all sciences where data exhibit spatial correlation. Theoretical properties of the spatial process are addressed under the distribution-free and likelihood-based perspectives. Strengths and weaknesses of these two dominant methodologies for modeling spatial correlation and predicting responses at unsampled sites and areal units are explored. Examples of hot spot detection and areal prediction show the flexibility of the Bayesian paradigm. Current bottlenecks and future directions in the field of geostatistics are discussed.