MAS8383 : Statistical Learning Methodology
- Offered for Year: 2019/20
- Module Leader(s): Dr Wentao Li
- Owning School: Mathematics, Statistics and Physics
- Teaching Location: Newcastle City Campus
|Semester 1 Credit Value:||10|
More data than ever before are being generated and stored, in a variety of fields across industry. The term "big data" has emerged in acknowledgement of the vast amounts of data now available. By applying statistical analyses to these data sets, we can start to use them to answer important questions such as (i) which are the important factors affecting the quality of an industrial process; (ii) how many different types of customer are interested in your product. Commonly the data sets that arise in industry are multivariate, comprising a large number of observations on many variables. In this module we study how we can learn from data sets of this form. Attention is paid to the statistical and mathematical theory underpinning the methods, in addition to their practical application using R.
Specifically, the module aims to equip students with the following knowledge and skills:
- To gain an understanding of the theory behind modern statistical approaches to learning from data.
- To gain experience in the application of these techniques to the analysis of large and complex data sets across a range of application areas.
Outline Of Syllabus
- Fundamentals of multivariate data analysis, including data representation, summary and core applications of linear algebra
- Theory and practice of principal components analysis
- Cluster analysis
- Linear regression, including variable selection, regularisation (ridge regression, the lasso, the elastic net) and dimension-reduction techniques
- Classification, including discriminant analysis and logistic regression
- Generalized linear models
- Tree-based methods, including regression trees, classification trees and random forests
|Scheduled Learning And Teaching Activities||Lecture||12||2:00||24:00||Lectures|
|Scheduled Learning And Teaching Activities||Practical||12||2:00||24:00||Computer Practicals|
|Guided Independent Study||Project work||1||32:00||32:00||Project|
|Guided Independent Study||Project work||4||5:00||20:00||Coursework|
Teaching Rationale And Relationship
Lectures are used for the delivery of theory and explanation of methods, illustrated with examples, and for giving general feedback on marked work. Practicals are used both for solution of problems and work requiring extensive computation and to give insight into the ideas/methods studied. A large number of practicals are scheduled in order to provide sufficient hands-on training and rapid feedback on understanding.
The format of resits will be determined by the Board of Examiners
|Practical/lab report||1||M||45||Up to three practical reports. Word count: up to 1000 words as specified for each report|
|Report||1||M||55||Project report Word count up to 1500 words|
Zero Weighted Pass/Fail Assessments
|Oral Examination||M||A structured discussion including a software demonstration and reflection on the key learning objectives of the coursework project|
Assessment Rationale And Relationship
Written assignments (approximately 3 pieces of work of approximately equal weight) followed by a larger piece of project work allow the students to develop their problem solving techniques, to practise the methods learnt in the module, to assess their progress and to receive feedback; the smaller pieces of work are thus formative as well as summative assessment.
The semi-structured interview facilitates a reflective discussion about how individual students have met the learning objectives of the module and how the principles of fundamental statistics are embedded in the functionality of their project work.