Data Analysis
This course covers fundamental aspects of data analysis for physics and astronomy students.
You are not expected to have background knowledge in statistics, or computer programming, but both will ultimately be necessary in this class.
The first week will cover fundamentals. Then we will cover principles of data analysis, leading into practical situations. The assessments will include problem sets and an assignment, and a compulsory viva where you will be interviewed about your work. The viva helps ensure that you understand the work that you have submitted in this class, and it highlights that the practice of data analysis requires you to be an effective communicator even among audiences of non-technical people. It’s not enough to be able to do something: you also have to be able to explain what you have done, and defend your reasoning.
Week 1: Fundamentals
Week 2: Workflow & Model Building
- Practical Guide to Principled Bayesian Inference
- Fitting A Line To Data I
- Fitting A Line To Data II
Week 3: Optimization and Sampling
- Optimisation
- Markov Chain Monte Carlo Fundamentals
- Markov Chain Monte Carlo Practicals
Week 4: Model Representation and Selection
- Linear Models
- Latent Variable Models
- Comparing And Selecting Models
Week 5: Advanced Models
- Gaussian Processes I
- Gaussian Processes II
- Hierarchical Models
Week 6: Missing Data and Latent Variables
- Missing Data and Selection Effects
- Time Series