Data in movement science are rarely simple. The same people are measured several times, under several conditions, often with outcomes that are skewed, counted or binary. This seminar teaches one framework that handles all of this: the linear model and its extension, the mixed model. Classical tests such as the t-test, ANOVA and regression turn out to be special cases of the same model, which grows step by step throughout the semester.

Each session combines a short input with practical work. We collect our own data in class (reaction times, balance, jumps, heart rate) and analyse them in Python with kbstatpy on Google Colab, without any installation. Part A leads from the t-test to the linear mixed model; Part B in the summer semester continues with individual curves, non-normal outcomes and a research project.