Host Institution
ICPSR and the University of California, Santa Barbara

Instructor
Luc Anselin
University of Illinois, Urbana-Champaign

The Workshop
This course provides an introduction to and overview of the application of spatial data analysis techniques in empirical social science research. With the exponentially growing use of geographic information systems (GIS) to store, manipulate and visualize geocoded information, it is increasingly important to understand the particular nature of geographic data and the specialized statistical techniques required for its analysis.

The focus of the course is on how techniques for the analysis of spatial data can be effectively applied in a GIS environment, with a particular emphasis on the study of spatial patterns and spatial autocorrelation, such as the detection of clusters, outliers and any other relationships that pertain to the absolute and relative location of observations. Common applications of spatial data analysis techniques in the social sciences range from the discovery of crime clusters, hot spots and the detection of disease clusters, to spatial autocorrelation of demographic variables and regression models for real estate analysis.

The course reviews five main aspects of spatial data analysis:

(1) spatial data visualization and exploration (including the application of dynamically linked windows);
(2) the analysis of clusters and point patterns (including space-time cluster statistics);
(3) global and local indicators of spatial autocorrelation (including LISA and visualization of spatial autocorrelation);
(4) variogram analysis (basic concepts of geostatistics); and
(5) introduction to spatial regression analysis.

The main focus will be on data description and exploration. More advanced topics pertaining to spatial regression analysis are not considered here, but treated in a separate course. In addition to an overview of the main methodological issues and most commonly used test statistics, an important component of the course is to gain hands-on experience in the use of a range of software tools such as SpaceStat, CrimeStat and various extensions to commercial GIS products.

Prerequisites include a familiarity with multivariate statistics and basic concepts of probability theory, as well as a some knowledge of desktop GIS software (for example, as gained from the interactive web tutorials provided by several vendors).

The course will be held on the beautiful, coastal campus of the University of California, Santa Barbara.

[TOP]