The course aims to focus mostly on showing how to use statistical tools, rather than giving a detailed introduction to theory behind probability and statistics. There are many great books and courses on this topic, which I encourage you to look at before the lectures. The resources listed here all are available online, either directly or through the ETH library.
- Weighing the odds, a course in probability and statistics, Williams, 2001 ETH library. A good introduction to probability theory and statistics with a high level of mathematical rigour.
- Bayesian Data Analysis, Gelman, 2013 ETH library. The title says it all.
- Information Theory, Inference, and Learning Algorithms, MacKay, 2003 Link. Heavy on the information theory but also covers inference methods nicely. The exercises come with solutions.
- Practical Statistics for Astronomers, Wall, 2012 ETH library. Short, with a focus on practical applications. Many of the examples and exercises are from astrophysics but are generally applicable, especially for the physical sciences, which often come a bit short in general statistics textbooks. Solutions and data sets are available online.
lessons: The lesson notebooks, which are used to create the slidesslides: Slides for the lessonspdf: PDF versions of the lecture notebooksexercise_solutions: Solutions to selected exercisescourse_tools: Tools for creating this course, such as a script to generate the slides from the notebooks and a python package with helper functions.
If you are seeing this in the course JupyterLab, you are probably in the directory with the course materials:
To make your live easier later on with version control, go up one level in the directory structure and make your own directory for the code you are going to write in this course:
All the materials can be access outside of JupyterLab as well. The repository with the course materials can be found on github.
To set up your own computing environment I strongly recommend anaconda. Either using miniconda or the much faster mamba implementation.