Â鶹´«Ã½ÊÓƵÍøÕ¾

This module aims to provide an introduction to regression modelling, covering linear, generalised linear and generalised additive modelling, and with an emphasis on ideas, methods, applications and interpretation of results. It is primarily intended for second year students registered on the undergraduate degree programmes offered by the Department of Statistical Science (including the MASS programmes). It also serves as a core module for students taking the Mathematics and Statistics stream as part of the Natural Sciences degree.ÌýFor all these students, the academic prerequisites for this module are met through compulsory study earlier in their programme.

Intended Learning Outcomes

• have an understanding of the basic ideas underlying multiple regression,Ìýgeneralised linear models and generalised additive models;
• be able to use the R statistical computing software environment to build theseÌýregression models;
• understand the assumptions underlying theÌýanalyses,Ìýknow how to check their validity and interpret the results.

Applications - Regression modelling is a powerful statistical tool to model and analyse the relationship between random variables, and is widely used in almost all of classical and modern statistical practice. Its use exemplifies the modern, model-based approach to statistical investigations, and provides the foundations for more advanced techniques that may be required for the study of complex systems arising in areas such as economics, natural and social sciences and engineering as well as in business and industry.

Indicative Content -ÌýMultiple regression: model fitting by least squares. Introduction to the exponential family of distributions. Generalised linear models: model fitting by maximum likelihood estimation. Generalised additive models: model fitting by penalised maximum likelihood estimation. Procedures for model assessment, including the scrutiny of residuals, and model selection.

Key Texts - Available from .