Track: Ecology, Conservation, and Archaeology
Predictive Locational Modeling of Archaeological Resources Using the S-PLUS/ArcView GIS Link
James A. ZeidlerPredictive archaeological modeling and the development of "probability surfaces" for archaeological resource location have been carried out in GIS environments for some two decades with increasing sophistication and statistical robustness. One hindrance has been the lack of a suitable multivariate statistical algorithm operating within a particular GIS package. Using a new linkage (beta) between MathSoft's S-PLUS statistical software package and Esri's ArcView GIS, this paper explores the application of logistic regression for purposes of developing predictive models of archaeological resource distribution across a landscape through probability surface mapping. The method is illustrated with an example from central Kansas.
James A. Zeidler
U.S. Army Corps of Engineers
P.O. Box 9005
Champaign, IL 61826-9005
USA
Telephone: 217-373-4572
Fax: 217-373-4421
E-mail: j-zeidler@cecer.army.mil