Linear statistical modelling
This module covers statistical modelling where a response variable depends on one or several explanatory variables: such as how well patients respond to a treatment, given their age and disease severity; or how different strains of wheat compare when grown in various conditions. Taking a practical approach, you’ll use real problems and data to stimulate analyses and their interpretation. Statistical tools are introduced, and use of the statistical software package, GenStat (supplied) is taught. You need a reasonable understanding of basic statistical ideas, as developed by Analysing data (M248). You’ll learn to use the most important methods of analysing data – a skill that too few people have.
What you will study
This module is about the statistical modelling of situations in which a response variable depends on at least one explanatory variable. It offers a practical treatment of an important area of statistical methodology, applicable in a wide variety of situations. For example, it enables us to deal with questions such as how cavity wall insulation will affect the total energy consumption of a house; or how the probability of a successful bone marrow transplant is influenced by the ages of the donor and recipient, and other factors; or how loss due to abrasion might depend on the hardness and tensile strength of samples of rubber.
Linear statistical modelling uses real problems and data to stimulate analyses and their interpretation. Technical background is not ignored, but the main emphasis is on the knowledge needed to analyse data effectively.
The module begins with a general introductory unit, including a review of the general statistical methods and concepts that will be used later. The next unit gives a complete introduction to using the statistics package GenStat for Windows (which is supplied). We then move on to the basic linear regression model, extensions of which are the core of this module.
Subsequent units introduce a wide variety of linear statistical modelling tools: one-way analysis of variance, multiple regression, more general analysis of variance and designed experiments. All these are widely applicable cases of the normal linear model.
Further units develop linear modelling in the more general framework of the generalised linear model: binary regression; the full generalised linear model; diagnostic checking; and log-linear modelling.
A closing unit applies the methods you have learnt to the analysis of further data sets.
The GenStat package is extensively used throughout the module to perform the necessary calculations and analyses.
You will learn
Successful study of this module should enhance your skills in analysing and interpreting data.
This module may help you to gain membership of the Institute of Mathematics and its Applications (IMA). For further information, see the IMA website.
This module may also help you to apply for the professional award of Graduate Statistician conferred by The Royal Statistical Society (RSS).
Module books, website, and online forums.
You will need
Calculator (basic mathematical functions would be useful).
You require access to the internet at least once a week during the module to download some essential module resources and to keep up to date with module news.
A computing device with a browser and broadband internet access is required for this module. Any modern browser will be suitable for most computer activities. Functionality may be limited on mobile devices.
Any additional software will be provided from a hardware device e.g. DVD drive or USB stick or is generally freely available. However, some activities may have more specific requirements. For this reason, you will need to be able to install and run additional software on a desktop or laptop computer with Windows 7 or higher.
The screen of the device must have a resolution of at least 1024 pixels horizontally and 768 pixels vertically.
To participate in our online-discussion area you will need both a microphone and speakers/headphones.
Our Skills for OU study website has further information including computing skills for study, computer security, acquiring a computer and Microsoft software offers for students.