Environmental Spatial Data Analysis
This advanced GIS course focuses on frequently used quantitative methods in spatial analysis in the R programming environment. These can help us answer questions such as: are features of interest in my study area spatially clustered or independently distributed? I have field-collected point data – how can I interpolate between points to make a spatially continuous map? Is my data spatially autocorrelated? And if so, how does it affect my analysis. What underlying variables best explain or predict the patterns of land cover in my study area? Thus, course topics include: use of R in spatial analysis, assessment of spatial autocorrelation, spatial point pattern analysis and clustering analysis, spatial interpolation, and spatial regression analysis. Course format emphasizes hands-on lab work, and uses R (and some ArcGIS). Labs (homework) will require some additional time to finish outside of the lab time. Prerequisites: one GIS course (e.g. EAS 531 or similar), one introductory statistics course (e.g. EAS 538 or similar), basic familiarity with the R environment (if no previous R experience contact instructor for permission to enroll, some preparatory work may be required).