The aim is to make the students familiar with the most important statistical methods that are employed in the analysis of experimental data. An essential part of the lecture is the demonstration of the methods on real or simulated data sets that are representative for the experimental situation. All algorithms are implemented in Matlab and will be given to the students along with the data sets.
1. Descriptive statistics: How do I present my data in a concise, but meaningful way? 2. Stochastic modeling: How do I construct a model of my data that correctly describes the random aspects of an experiment, and which models are relevant in the experimenter's practice? 3. Parametric estimation, confidence intervals: How do I estimate physical quantities from my data, and how do I asses the uncertainty of the estimates? 4. Linear regression: Is there a correlation between two or more observed quantities, and how is it quantified? 5. Modelling of background, robust methods: How do I separate the signal from the experimental background, and how can I minimize the influence of the background? 6. Parametric and non-parametric tests: How do I test whether my data show significant deviations from theory? 7. Simulation: Why should I simulate my experiment and how can I do it?
The handout (4 slides per page) can be downloaded by the registered students. Recommended books: L. Lyons, A practical guide to data analysis for physical science students, Cambridge University Press, 1991. L. Lyons, Statistics for Nuclear and Particle Physicists, Cambridge University Press, 1986. W. Stahel, Statistische Datenanalyse: Eine Einführung für Naturwissenschaftler, Vieweg+Teubner, 2007. V. Blobel und E. Lohrmann, Statistische und numerische Methoden der Datenanalyse, Teubner, 1998. L. Fahrmeir et al., Statistik: Der Weg zur Datenanalyse, Springer, 2007. S. M. Ross, Statistik für Ingenieure und Naturwissenschaftler, Spektrum, 2006.
