Hints and tips:
  • You may need to look up some unfamiliar terms in the title or description to get more of a sense of what is involved.
  • If the project has "No" in the "Current Availability:" field, it is already taken or not being offered this academic year but may be available again in future years.
  • The supervisor name links to a contact details webpage so, if you are interested, you can arrange to discuss this project or even propose a related topic of your own.
Level: BSc, MSci, MSc
Title: Multivariate Distribution Theory
Supervisor:

Dr Steve Coad
Research Area: Probability and Applications [Including Statistics]
Description:

When data consist of observations on more than one variable, it is often assumed that they follow a multivariate normal distribution. One of the reasons for making this assumption is that the underlying theory is usually tractable, though complicated. The first part of the project involves the study of some properties of the multivariate normal distribution. Other possible topics include the non-central \chi^2 and F distributions, distributions of quadratic forms, spherical and elliptical distributions, and distributions of correlation coefficients. A study of some of these topics leads to a better theoretical understanding of certain results met in earlier Statistics and Probability courses.
Further Reading:
  • K. Mardia, J. Kent, J. Bibby, Multivariate analysis. Academic Press, Cambridge, MA, 1979.
  • R. Muirhead, Aspects of multivariate distribution theory. Wiley, Chichester, 1982.
Key Modules:

MTH5112 Linear Algebra I

MTH5121 Probability Models
Other Information:

A good knowledge of matrix algebra is required for the project.
Current Availability: Yes