Spatial Statistics Wei Ding, Spring 2007
Some Thoughts • It is hard to find a general spatial statistics paper. In the following slides, I recommend a workshop, a professor, two websites, and one book, which are related with spatial statistics.
A Good WorkshopShort Course: Introduction to Spatial Data Analysis at UIUC, Luc Anselin • The course is organized into six broad topics (http://www.csiss.org/events/workshops/2002/data2002/outline.pdf): • Concepts: what makes spatial data analysis different, some basic GIS concepts, understanding of the paradigms in spatial data analysis • Geovisualization: the visualization and exploration of spatial data, dynamically linked windows, outlier analysis, smoothing of maps for rates. • Point pattern analysis: assessing whether a pattern of locations (points) is clustered, spatial point processes, nearest neighbor statistics, second order statistics, bivariate and space-time point patterns. • Spatial autocorrelation analysis: descriptive statistics for spatial autocorrelation, constructing spatial weights, visualizing spatial autocorrelation, local indicators of spatial association, multivariate spatial correlation • Geostatistics: the geostatistical perspective, variograms, kriging • Spatial regression: specifying spatial econometric models, spatial externalities, estimation methods, specification tests Wei: please read the course outline, it includes many good paper references
An Interesting Professor • http://sal.uiuc.edu/users/anselin/ • Research Projects • Geovisualization and Spatial Analysis of Cancer Data (NCI) • The sensitivity of concentration-response functions to the explicit modeling of space-time dependence (NSF/EPA) • Center for Spatially Integrated Social Science (NSF) • A web-based spatial analytic toolkit for the study of homicide data (NCOVR)
A Good Website • the Center for Spatially Integrated Social Science (CSISS) main site, especially its learning materials, syllabi and search engines, http://www.csiss.org/ • Summer Workshops 2002 Video Clips - Spatial Pattern Analysis in a GIS Environment http://www.csiss.org/streaming_video/2002/spa.html • The Nature of Spatial Pattern Analysis, Art Getis • Problems Associated with Spatial Pattern Analysis, Art Getis • An Introduction to GIS, Mike Goodchild • GIS Functionality, Mike Goodchild • Current Technologies in GIS, Mike Goodchild • Spatial Patterns of Birth Data, John R. Weeks • Spatial Patterns of Fertility in Egypt, John R. Weeks Wei:I checked several clips, the quality is good.
Another Good WebsiteSpatial Statistics Softwarehttp://www.spatial-statistics.com/ • The company website collects useful information on • Spatial autoregressions (SAR) • Conditional spatial autoregressions (CAR) • Mixed regressive spatially autoregressive (MRSA) • Exact log-determinant computations • Nearest neighbors • Contiguity/contiguous observations • Spatial temporal routines • Multivariate dependence • Matrix exponential spatial specifications • Doubly stochastic weight matrices • Spatial autoregressive local estimation • Log-determinant approximations
A Good Book http://www.amazon.com/Elementary-Statistics-Geographers-James-Burt/dp/0898629993 • It is a popular textbook used by undergraduate or first year graduate students. • Review"It has been difficult to find a good introductory statistics text that can be used with a class consisting of both physical and social science students. This textbook meets that demand by incorporating a good number of examples from both aspects of the discipline and including thorough discussions of introductory spatial statistics....Should prove useful as both a classroom textbook and a basic statistical reference." -David R. Legates,University of Oklahoma"Burt and Barber have extended and modernized a text that has long served geography students as a methodological foundation....This text will find its place in upper-level undergraduate courses and first-year graduate study for those with limited statistics backgrounds." -Randall W. Jackson,Ohio State University"The text is very well organized and contains a wealth of excellent examples and diagrams. Chapters on time-series and computer-intensive methods are particularly valuable."-Scott Robeson, Indiana University