This paper presents a GIS-based program that fully automates the measu
rement of spatial autocorrelation. In addition to being operational an
d practical, the program is flexible, as it allows the researcher to t
est alternative definitions of locational proximity between area objec
ts. The program is applied to the study of the spatial impact of growt
h-control policies in the San Francisco Bay Region. This application e
xample demonstrates that the technique of spatial autocorrelation is p
otentially useful for the study of the spatial consequences of public
policies, and that GIS can effectively facilitate this kind of study.