The course provides a broad introduction to advanced statistical modeling tools. Starting from the fundamental linear regression models, we investigate modelling of non-linear (but parametric) relationships between explanatory and response variables. We then consider the Generalized Linear Models (GLM), which model a function of the expected value, rather than the expected value itself. This methodology includes binary response (0/1) data modelling and the modelling of count and proportion data. We further investigate the Generalized Additive Models (GAM) with the response being modelled in terms of explanatory variables without explicitly assumed parametric relationship. We also incorporate the GAM methodology in the GLM setting, allowing for the modelling of various types of responses with complex structure dependencies on explanatory variables. We also show how we can use Bootstrap methodology to perform inference and tests as an alternative to standard statistical procedures.
In a degree, this course may not be included together with another course with a similar content. If unsure, students should ask the Director of Studies in Mathematics and Mathematical Statistics. The course can also be included in the subject area of computational science and engineering.