290019 PS Environmental Statistics Using R (2013S)

Statistical methods for spatial environmental data include a broad range of techniques such as kriging interpolation, spatial regression and variogram analysis (geostatistics), spatial point pattern analysis, all of which address the common issue of spatial autocorrelation in spatial data. Other environmental applications in remote sensing, geomorphology and biogeography require the use of advanced classification methods such as generalized additive models or the support vector machine. Applied statistical data analysis furthermore requires the integration of statistical software with geographical information systems.
This course will give an introduction to selected statistical techniques for environmental data analysis, and provide an opportunity to acquire statistical computing skills using real-world data sets and hands-on exercises. We will use the high-level scripting language R (www.r-project.org) a free, yet professional data analysis environment that provides flexible and powerful tools needed for the analysis of complex geospatial data.
Students taking this course will furthermore find an opportunity to discuss statistical data analysis challenges encountered in their own Master’s or PhD research.