Objectives

The principal objective of this course is to provide a solid actuarial understanding of building, selecting and validating statistical models relevant to insurance business and related actuarial applications. This course aims at establishing a useful bridge and deep understanding between various statistical models of insurance contracts and the raw, typically incomplete, insurance portfolio data available to actuaries. Accompanying exercises in R will help to enhance data skills and understanding of complex computational tools utilised in actuarial applicaitons.

Contents

• Probabilistic Aspects of Insurance Contracts
• Parametric & Non-Parametric Approach
• Insurance Models with Incomplete Data
• Extreme Value Analysis
• Model Validation & Selection
• Generalised Linear Models & Extensions

References

• Statistical Theory. Seleznjev, O. Manuscript available in moodle.
• Generalized Linear Models for Insurance Data. Jong, P., Heller, G.Z. Cambridge University Press, Cambridge, 2008.
• Regression Modeling with Actuarial and Financial Applications. Frees, E.W. Cambridge University Press, Cambridge, 2009.
• Statistical Analysis of Extreme Values: From Insurance, Finance, Hydrology and Other Fields. Reiss, R-D., Thomas, M. 3rd Edition, Birkhäuser, Basel, 2007.
• Elements of Copula Modeling with R. Hofert, M., Kojadinovic, I., Mächler, M., Yan, J., Springer, 2019.
• Statistical Foundations of Actuarial Learning and its Applications. Wüthrich, M., Merz, M., 2022, (available here https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3822407)

Pre-requisites

Basics in statistics & probability

Evaluation

First attempt

Exam:

Written 3h00 hours

Documentation:

Not allowed

Calculator:

Not allowed

Evaluation:

Final Grade = Grade of Final Exam*

*Exam conditions may be subject to changes depending on the pandemic situation.

Retake

Exam:

Written 3h00 hours

Documentation:

Not allowed

Calculator:

Not allowed

Evaluation:

Final Grade = Grade of Final Exam*

*Exam conditions may be subject to changes depending on the pandemic situation.