Center for Demography of Health and Aging

The Applied Population Lab is offering three workshops on using GeoDa. GeoDa is software designed to provide a graphical interface to methods of descriptive spatial data analysis, such as spatial autocorrelation statistics, as well as basic spatial regression functionality. For more information about GeoDa, visit this site: https://www.geoda.uiuc.edu/.

October 3, 2008
9:30-11:30 Room 3218
Spatial Weights and Spatial Autocorrelation in Geoda
This lab uses the Spatial Statistical software, Geoda, to introduce students to the concept of spatial weights and measures of spatial autocorrelation. The weights matrix defines the spatial “neighborhood” and can take a number of forms. There is no “correct” choice of a spatial weights matrix, only well-reasoned ones. Using Geoda, we will use georeferenced sample data to construct different spatial weights matrices, then calculate measures of local and global spatial autocorrelation for our data.
Instructor: Long

October 10, 2008
9:30-11:30 Room 3218
Exploratory Spatial Data Analysis in Geoda
This lab introduces students to more of Geoda’s basic functionality. We will begin to undertake exploratory spatial analysis of sample data provided. Geoda includes tools for straightforward mapping along with statistical representations such as histograms and scatterplots. More importantly, however, these tools can allow users to examine how the statistical properties of their data change across space. This lab will also demonstrate similar functions in the opensource programming language, R.
Instructors: Buckingham & Long

October 17, 2008
9:30-11:30 Room 3218
Spatial Regression Analysis in Geoda and R
Again using Geoda, this lab introduces students to how to specify and interpret two regression models of spatial dependence: the spatial error model and the spatial lag model. The two approaches have different assumptions and theoretical implications about the form of the spatial process being analyzed. The spatial error model identifies spatial autocorrelation in the error structure of the regression model. The spatial lag model, in contrast, identifies spatial autocorrelation in the covariance structure of the dependent variable. This lab will also demonstrate implementation of these functions in the opensource programming language, R.
Instructors: Buckingham & Long

For events in the past, please see the Prior Meetings and Papers page.