This course will provide a comprehensive introduction to the principles and practice of advanced data analysis, with particular focus on their application within the physical sciences and on the (rapidly growing) use of Bayesian Inference methods. Over the past few decades Bayesian inference methods, as a powerful tool for analyzing data, have been growing ever more common across a diverse range of fields of physics. Bayesian inference provides a natural framework in which to address key quantitative questions, constrain the parameters of physical models and measure how well competing models can describe the available data. They also provide an objective and straightforward framework in which to incorporate prior information about those models, obtained e.g. from previous analyses or from theory. Moreover, recent advances in computational methods also offer simple algorithms in which to implement Bayesian methods – even with very large and complex data sets – on a standard desktop computer. These lectures will give a comprehensive introduction to Bayesian inference methods. The lectures will include some practical exercises designed to introduce some useful codes and algorithms – as well as to showcase the vast array of online resources available to support the “virgin Bayesian” seek to apply these methods to their data.
This course is taught via a series of lectures running in the SUPA VC rooms at each University
Lecturer: Ik Siong Heng
Hours Equivalent Credit: 10
Assessment: Continuous Assessment via series of multiple choice questions. Optional mock data challenge also available, although not compulsory.