Course Details in 2024/25 Session

Module Title	LI Multivariate Statistical Analysis
School	Mathematics
Department	Mathematics
Module Code	06 31299
Module Lead	Yin Jing
Level	Intermediate Level
Credits	10
Semester	Semester 1
Pre-requisites
Co-requisites
Restrictions	Available only to students on the JI dual degree pro-grammes
Exclusions
Description	The main contents of this module are: multiple regression, discriminant analysis, cluster analysis, principal component analysis, factor analysis, correspondence analysis, canoni-cal correlation analysis and multidimensional scaling meth-ods. Star plot, Chernoff-Flury Faces, Andrews’ Curves, and scatterplot matrices are used to represent multivariate data. Calculation methods for statistics, such as the mean vector, and covariance matrix are discussed. The module introduces matrix algebra, multivariate distributions, and data transformation. The R statistical programming pack-age is used throughout to illustrate the methods. Students will write a report about how they analysis real data using some of these multivariate statistical methods.
Learning Outcomes	By the end of the module students should be able to: Perform exploratory data analysis using graphical and statistical methods. Understand multivariate statistical models. Understand the effect of model assumptions in applications. Appreciate algorithmic differences among similar models. Write R programs for multivariate models, and analyse the results. Use multivariate statistical methods and software for real data modelling and analysis.
Assessment
Assessment Methods & Exceptions	Assesment: Assignments (20%) Paper Report (30%) : a maximum 1500 word report Final Exam (50%) : a 2 hour examination Re-assessment (where allowed): a 2-hour resit examination (100%)
Other
Reading List