|
Activity Number:
|
150
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 30, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistical Computing
|
| Abstract - #309852 |
|
Title:
|
Temporal Extensions to Spatial Statistical Metrics
|
|
Author(s):
|
James Shine*+ and James P. Rogers and Mete Celik and Shashi Shekhar
|
|
Companies:
|
U.S. Army Topographic Engineering Center and U.S. Army Corps of Engineers and The University of Minnesota and The University of Minnesota
|
|
Address:
|
4218 Alcott Street, Alexandria, VA, 22309,
|
|
Keywords:
|
spatial statistics ; spatio-temporal ; point patterns ; lattices ; random fields
|
|
Abstract:
|
A wealth of metrics have been developed to measure the statistical properties of different types of spatial data. Point patterns are described by metrics such as Ripley's K, intensity, and different nearest-neighbor measures. Lattices are described by metrics such as Moran's I, Geary's C and different forms of spatial regression models. Continuous random field models are described by metrics such as the variogram. As spatial research increasingly becomes spatio-temporal research, extensions of these spatial statistics to the temporal realm are being examined. In particular, extensions to Ripley's K have been discussed by Diggle and others. This paper will examine existing efforts to extend these spatial metrics to include the temporal dimension and will offer some new extension ideas as well.
|
