This course aims to give students a solid grounding in some of the most important statistical analysis methods in environmental sciences. Rather than being an introduction to descriptive analysis and statistical modelling, this module aims to be a bridge between an introduction to the field and the professional literature for graduate students in ecology, environmental science disciplines and energy systems. It provides students with an understanding of the empirical statistical techniques commonly used in environmental analysis; the ability to use these empirical techniques; the ability to critically evaluate and interpret empirical work; expertise in the use of an appropriate software package - R; and the skill to communicate the results of empirical work. Participants will require a sound knowledge of their own branch of natural science.

The course will demonstrate, based on practical examples, how data analysis in environmental sciences should be approached, outline advantages and disadvantages of methods. This approach also clearly demonstrates the limits of classical statistical data analysis with environmental (geochemical) data. The special properties of environmental data (e.g., spatial dependencies, outliers, skewed distributions, closure) do not agree well with the assumptions of "classical" (Gaussian) statistics. Applied earth science data call for the use of robust and non-parametric statistical methods. These techniques are extensively used and demonstrated in the course. The focus is on the exploratory use of statistical methods and statistical modelling of environmental data and energy systems.