See module specification for other years:
2019-202020-21
Module summary
The aim of the module is to expose students to a number of advanced statistical topics that are used in actuarial science and quantitative risk management, including Bayesian inferential procedures, credibility theory, extreme value theory, the modelling of dependent risks and machine learning
Module will run
Occurrence
Teaching cycle
A
Autumn Term 2021-22
Module aims
The aim of the module is to expose students to a number of advanced statistical topics that are used in actuarial science and quantitative risk management, including Bayesian inferential procedures, credibility theory, extreme value theory, the modelling of dependent risks and machine learning
Module learning outcomes
After successful completion the student is able to:
Subject content
apply Bayes and minimax decision rules;
use Bayesian inferential procedures;
apply Bayesian credibility theory to insurance tarification problems;
describe the main ideas of extreme value theory and dependence modelling via copulas;
demonstrate knowledge of the main concepts of machine learning.
Academic and graduate skills
present decision theoretic analyses in a logical, rigorous, and concise way.
strict logical reasoning from assumptions to conclusion;
critically assess assumptions necessary to draw certain conclusions.
Assessment
Task
Length
% of module mark
Essay/coursework Coursework
N/A
20
Online Exam Further Statistics for Actuarial Science
N/A
80
Special assessment rules
None
Reassessment
Task
Length
% of module mark
Online Exam Reassessment: Exam
N/A
100
Module feedback
Students will receive feedback within three weeks of the hand-in problem sets. The feedback will be handed to students personally and takes the form of comments and suggestions for improvement written on the handed in work.
Indicative reading
McNeil, A, Frey, R and Embrechts, P (2016), “Quantitative Risk Management: Concepts, Techniques & Tools” (2nd ed), Princeton University Press.