Close
Description
This module aims to introduce methodological, theoretical and applied foundations, along with illustrative examples, of some widely-used classical multivariate methods and modern high-dimensional methods. It is primarily intended for third year and fourth year undergraduates and taught postgraduates registered on the degree programmes offered by the Department of Statistical Science (including the MASS programmes). The academic prerequisite for these students (in addition to their compulsory modules) is听STAT0023 (UG) or STAT0030听(笔骋罢).
Intended Learning Outcomes
- understand methodologies and statistical assumptions underlying the different multivariate and high-dimensional methods learnt;
- be able to choose appropriate multivariate and high-dimensional methods for different datasets and data-analysis tasks;
- be able to implement multivariate and high-dimensional data analyses in the R statistical software package;
- a thorough understanding of the relationships between the different methods learnt (Level 7 only);
- be able to provide a critical appraisal of the strengths and weaknesses of the different methods learnt (Level 7 only).
Applications - Multivariate methods are some of the most researched and applied approaches in statistics and machine learning. High-dimensional methods prevail in recent decades, mostly thanks to technology modernisations enabling routine generation and collection of high-dimensional data. Both multivariate and high-dimensional methods have found applications in a wide range of fields, such as healthcare, security, finance, science and technology.
Indicative Content - Multivariate normal distribution, principal component analysis (PCA), canonical correlation analysis (CCA), linear discriminant analysis (LDA) for binary classification and multi-class classification, generative learning versus discriminative learning, partial least squares (PLS), penalised likelihood methods (especially ridge regression, lasso and generalisations), sparse multivariate methods, and model-based cluster analysis.
Key Texts - Available from .
Module deliveries for 2024/25 academic year
Last updated
This module description was last updated on 19th August 2024.
听