Summer Schools and Workshops
16th International Summer School 2003
of the Swiss Association of Actuaries on
Credibility and Its Applications
Monday, Sep. 22 to Friday, Sep. 26, 2003
| Faculty |
Experienced teachers, including Prof. Hans Bühlmann
and Prof. Alois Gisler
as main lecturers. |
| Brief outline |
The course is based on the revised material from the lectures by
Professors Hans Bühlmann and Alois Gisler at the Swiss Federal Institute of Technology Zurich.
The main topics are
- Basic concepts
- Individual and collective premiums
- Credibility premium as a practical way to find the
best experience rating procedure
- Standard models
- Bühlmann-Straub
- Regression (Hachemeister)
- Hierarchical
- Multidimensional
- Treatment of large claims
- State space modelling
- Evolutionary models
- Reinterpretation of the collective in an
evolutionary setting
|
| Language |
English |
| Participants |
Practicing actuaries as well as researchers with knowledge of
probability and statistics. |
| Fee |
Swiss Francs 1,400. This price includes tuition, hotel
accommodation (single room) and full board. |
| Location |
Hotel Seeblick,
CH-6376 Emmetten (near the Lake
of Lucerne). |
| Dates |
Monday, September 22 (morning) to Friday, September 26 (noon)
2003. The participants are expected to arrive on Sunday, September 21,
2003. |
| Registration |
Please download the registration
form. |
| Deadline |
Please register before April 30, 2003 |
Dependence Modelling for Credit Portfolios
Venice, Sep. 22-23, 2003
Scientific Committee
Further
information
Lecturers
Prof. Dr. Paul Embrechts
(ETH Zürich)
Roger Kaufmann (RiskLab, ETH Zürich)
Course Description
An alternative title for this course would be: "Beyond Value-at-Risk
and beyond linear correlation: more realistic tools for Integrated Risk
Management." Both notions, extremes and dependence, on the one hand
belong to the core of any quantitative risk management system, on the
other hand, they are probably the least well understood. This one week
course critically assesses the methodological assumptions underlying
modern Integrated Risk Management (IRM) and presents Extreme Value
Theory (EVT) as a useful set of techniques needed to understand why
certain Risk Management (RM) tools do not deliver what they promise.
Special attention will be given to the interplay between rare (extreme)
event occurrence and the behavior of correlations.
Objectives
The participant will learn about the instruments needed for critically
assessing the strengths and weaknesses of modern RM tools. A deeper
understanding of the need for integrating actuarial and banking thinking
in setting up a well-functioning IRM system will be obtained. Through a
combination of teaching new methodology (i.e. EVT, copulas) together
with case studies both from insurance and finance, the participant will
better grasp the possibilities as well as limitations for modeling rare
events and their RM consequences. In order to achieve this goal,
practical sessions using specific software will be organized.
Target Audience
Risk managers, quants, actuaries in banking, insurance and general
corporations, as well as RM experts in supervisory authorities. As the
course is set at a quantitative level, participants are expected to have
the necessary background to follow discussions on quantitative RM. A
basic knowledge of elementary probability and statistics is presupposed:
the course aims very much at understanding why and how certain
techniques work without entering into unnecessary technicalities.
Course Content
- Extreme Value Theory
The basics, how to use EVT in analyzing rare events, from data to
model, strengths and weaknesses of EVT, an outlook on current EVT
research within finance and insurance, available EVT software (including
a demonstration and computer assisted exercises).
- VaR and Beyond
A critical assessment of the classical Value-at-Risk (VaR) methodology,
how to use EVT in order to go beyond VaR, how to measure shortfall risk,
dynamic risk measures, coherence.
- Dependence
The modeling of dependence is key to modern finance. The notion of
correlation will be critically assessed, pitfalls discussed and
alternative approaches (like copulas) presented.
- Applications to the Analysis of Market, Credit and Operational
Risk
Developing superior stress testing methodology in IRM using EVT and
copulas.
- Examples and Exercises
As the main aim of the course is a practical understanding of current
and new RM tools in use (or future use) new techniques will always be
explained on relevant data from insurance and finance. Students will
have the possibility to analyze data themselves.
Reference
Participants will receive copies of relevant course material. Course
related work is to be found under http://www.risklab.ch/Papers.html.
Workshop on
Extremal Events and Dependence Modelling
with Applications to Financial Risk Management
Swiss Re, Rüschlikon,
Nov. 12 - 13, 2001
Seminar Leaders:
Aim of the Workshop
Risk managers are primarily concerned with the risk of
low-probability events that could lead to catastrophic losses. Yet
traditional VaR methods tend to ignore extreme events. In particular, it
is often assumed that log-returns are multivariate normally distributed,
and little attention is paid to the distribution of the (possibly
dependent) extreme returns we are most concerned about. The danger is
then that our models are prone to fail in situations when they are
needed most - in the event of large market or credit losses. Attempts to
estimate the probability and severity of such large losses are hampered
by the lack of data - unusually large market or credit losses are almost
by definition rare events. Extreme Value Theory (EVT) is a set of
statistical techniques that have been developed to deal with these
problems.
Financial risk management also confronts us with complex
interdependencies. Of particular concern for risk managers is the issue
of extremal dependence - the phenomenon of increased dependence and
reduced diversification in stress periods. Copulas give us the very
latest tools for understanding and modelling this phenomenon and show
how extreme value theory may be taken to higher dimensions. Elliptical
distributions and the corresponding robust estimation of dependence are
a prominent example.
All these mathematical and statistical techniques help the financial
risk manager to make the best possible use of what little information we
have about the extreme losses and their possible dependence, which
explains why in recent years these techniques have become increasingly
popular as a risk management tool.
This two-day event consists of a systematic introduction to extreme
value theory and dependence modelling with a strong focus on
applications in financial risk management and worked-out case studies,
including live presentations with the latest version of the free EVIS
software routines (Extreme Values in S-Plus) developed at ETH Zurich as
an add-on to S-Plus.
Detailed seminar outline and
registration
Organizing Committee
Objectives
Advances in financial modelling and risk management are the two
topics of this tutorial. By bringing together leading experts from the
fields of mathematics of finance and optimization you will learn about:
- dependence modelling with applications to credit risk,
- the newest achievements in coherently measuring risk,
- designing and pricing financial products,
- analyzing and optimizing financial portfolios,
- gaining insight into the great progress made in capturing the
value of managerial flexibility using an option-based framework
(real options).
Whoever attends this tutorial will learn about the strong economic
and mathematical principles in dealing with the full ramifications of
uncertainties in financial investments, resource-allocations and
planning decisions.
Speakers and
registration details
Lecturers:
An alternative title for this course would be: «Beyond
Value-at-Risk and beyond linear correlation: more realistic tools for
Integrated Risk Management.» Both notions, extremes and
dependence, on the one hand belong to the core of any quantitative risk
management system, on the other hand, they are probably the least well
understood.
This one week course critically assesses the methodological
assumptions underlying modern Integrated Risk Management (IRM) and
presents Extreme Value Theory (EVT) as a useful set of techniques needed
to understand why certain Risk Management (RM) tools do not deliver what
they promise. Special attention will be given to the interplay between
rare (extreme) event occurrence and the behavior of correlations.
Course Content
- Extreme Value Theory: the basics, how to use EVT in analyzing
rare events, from data to model, strengths and weaknesses of EVT, an
outlook on current EVT research within finance and insurance, available
EVT software (including a demonstration and computer assisted exercises).
- VaR and Beyond: a critical assessment of the classical
Value-at-Risk (VaR) methodology, how to use EVT in order to go beyond
VaR, how to measure shortfall risk, dynamic risk measures, coherence.
- Dependence: the modeling of dependence is key to modern finance.
The notion of correlation will be critically assessed, pitfalls
discussed and alternative approaches (like copulas) presented.
- Applications to the Analysis of Market-, Credit- and Operational
Risk: developing superior stress testing methodology in IRM using EVT
and copulas.
- Examples and Exercises: as the main aim of the course is a
practical understanding of current and new RM tools in use (or future
use) new techniques will always be explained on relevant data from
insurance and finance. Students will have the possibility to analyze
data themselves.
Reference:
Participants will receive copies of relevant course material. Course
related work is to be found under http://www.risklab.ch.
Workshop on
Friday, May 11, 2001, Juans-Les-Pins, South of France
Seminar Leaders:
About this Seminar
Financial risk management confronts us with a real world of
heavy-tailed risks, rapid changes and complex interdependencies, which
force us to go beyond standard statistical models and simplifying
assumptions of multivariate normality to develop more sophisticated
methodologies for handling dependent risks. Of particular concern in
risk management is the issue of extremal dependence - the phenomenon of
increased dependence and reduced diversification in stress periods.
Copulas give us the very latest tools for understanding and modelling
this phenomenon and show how extreme value theory may be taken to higher
dimensions.
Seminar Outline
- Understanding the Fundamentals of Modelling Dependent Risks
- Examining Advanced Concepts in Dependent Risk Modelling:
Exploring Copulas and Extremal Dependence
- Evaluating The Latest Theoretical Advances & Practical
Techniques For Calibration and Simulation of Multivariate Models
- Evaluating The Application Of Multivariate Models And Copulas To
Credit Risk
- Evaluating The Extension To Other Applications: Market Risk and
Risk Integration
Lecturers:
Scientific Organization:
Prof. Dr. Karl-Theodor Eisele
Magistère d'Actuariat
Université Louis Pasteur
Strasbourg
Aim of the Workshop
The aim of this workshop is to provide participants with a clear and
comprehensive overview of extreme value theory (EVT) and its role in the
management of risk, whether market, credit, operational or insurance.
The emphasis will be on making the theory accessible and putting the
methods into practice. Using examples and case studies, your
instructors will take you through the mathematical, statistical and
computational aspects of EVT, including tuition in the free EVIS
software routines developed at ETH Zurich as an add-on to S-Plus. This
seminar is for risk managers who want to get up to speed with EVT
quickly and who want to realise the potential of state-of-the-art EVT
methods for concrete risk management problems.
Program of the Workshop
Session I: Extreme Value Theory (EVT) in Risk Management (RM)
- Rare events, heavy tails and EVT
- General principles of risk measurement
- Measures of tail risk - VaR and coherent measures beyond VaR
Session II: EVT: Basic Results
- The peaks-over-thresholds (POT) method
- Modelling tails of probability distributions
- Estimating measures of tail risk including VaR
- A comparison of EVT and historical simulation
- Maxima and worst-case losses
Session III: EVT and Market Risk Management
- Embedding EVT in a stochastic volatility framework
- Dynamic and static risk measurement
- VaR estimation and backtesting
- VaR for longer time horizons - scaling rules
Session IV: Other Applications of EVT
- Application of EVT to operational and insurance risks
- EVT and Credit Risk
- Software for EVT - the EVIS template
Session V: EVT and Correlation Risk
- Shortcomings of correlation as dependence measure
- Other approaches to dependence including copulas
- Extremal dependence and multivariate extreme value theory
- Monte Carlo generation of dependent risks and applications
Session VI: Case Study: EVT and Securitisation of Insurance
Risk
- Applying EVT to price catastrophe covers
- Data analysis and mastering practical obstacles such as censoring
- The art of modelling and testing for trends
- Identifying and quantifying model risk
- Implementing Monte Carlo scenario generation to assess robustness
- Calculating the coupon value of a CAT bond
Lecturers:
Aim of the Workshop
The aim of this workshop is to provide participants with a clear and
comprehensive overview of extreme value theory (EVT) and its role in the
management of risk, whether market, credit, operational or insurance.
The emphasis will be on making the theory accessible and putting the
methods into practice. Using examples and case studies, your instructors
will take you through the mathematical, statistical and computational
aspects of EVT, including tuition in the free EVIS software routines
developed at ETH Zurich as an add-on to S-Plus. This seminar is for risk
managers who want to get up to speed with EVT quickly and who want to
realise the potential of state-of-the-art EVT methods for concrete risk
management problems.
Program of the Workshop
Session I: Extreme Value Theory (EVT) in Risk Management (RM)
- Rare events, heavy tails and EVT
- General principles of risk measurement
- Measures of tail risk - VaR and coherent measures beyond VaR
Session II: EVT: Basic Results
- The peaks-over-thresholds (POT) method
- Modelling tails of probability distributions
- Estimating measures of tail risk including VaR
- A comparison of EVT and historical simulation
- Maxima and worst-case losses
Session III: EVT and Market Risk Management
- Embedding EVT in a stochastic volatility framework
- Dynamic and static risk measurement
- VaR estimation and backtesting
- VaR for longer time horizons - scaling rules
Session IV: Other Applications of EVT
- Application of EVT to operational and insurance risks
- EVT and Credit Risk
- Software for EVT - the EVIS template
Session V: EVT and Correlation Risk
- Shortcomings of correlation as dependence measure
- Other approaches to dependence including copulas
- Extremal dependence and multivariate extreme value theory
- Monte Carlo generation of dependent risks and applications
Session VI: Case Study: EVT and Securitisation of Insurance
Risk
- Applying EVT to price catastrophe covers
- Data analysis and mastering practical obstacles such as censoring
- The art of modelling and testing for trends
- Identifying and quantifying model risk
- Implementing Monte Carlo scenario generation to assess robustness
- Calculating the coupon value of a CAT bond
Lecturers:
Course outline:
- This one week course critically assesses the methodological
assumptions underlying modern Integrated Risk Management (IRM) and
presents Extreme Value Theory (EVT) as a useful set of techniques needed
to understand why certain Risk Management (RM) tools do not deliver what
they promise. Also EVT is essential for understanding the occurrence of
rare events. Special attention will be given to questions and
methodology in common between insurance and banking.
- The participants will learn about the instruments needed for
critically assessing the strengths and weaknesses of modern RM tools. A
deeper understanding of the need for integrating actuarial and banking
thinking in setting up a well-functioning IRM system will be obtained.
Through a combination of teaching new methodology (i.e. EVT) together
with case studies both from insurance and finance, the participants will
better grasp the possibilities for modelling rare events. In order to
achieve this goal, practical sessions will be organized where students
will learn how to analyze financial and insurance data from an EVT
perspective. An introduction to S-plus will be given, enhanced by the
EVT-package EVIS developed at ETH Zürich by Alexander McNeil.
Course text:
P. Embrechts, C. Klüppelberg
and T. Mikosch:
Modelling Extremal Events for
Insurance and Finance,
Springer-Verlag, Berlin (1997).
Modelling Extremal Events for Insurance and
Finance
Georgia State University
Atlanta, Georgia, August 21-25, 2000
Lecturers:
Course outline:
- This course will focus on statistical modelling of extreme values
with examples including industrial fire insurance, floods, and equity
returns.
- It will provide a review and critique of Dynamic Financial
Analysis, Value-at-Risk, and integrated risk management with (non-life)
insurance and finance applications.
- Participants will gain hands-on experience working with practical
examples in GSU's computer lab.
- An overview of extreme value theory (EVT) will be given. The EVT
results will be used to complement existing risk management techniques
in finance and insurance. An overview of current integrated risk
management practice will be provided followed by a discussion of the
ways in which EVT offers a useful tool to go beyond existing measures,
such as Value-at-Risk (VaR). Special emphasis will also be given to the
analysis of dependent risks and multivariate EVT. Various examples based
on data from insurance and finance will be given. Students will be able
to work on real data using the specially designed package EVIS developed
by Alexander McNeil.
Course text:
P. Embrechts, C. Klüppelberg
and T. Mikosch:
Modelling Extremal Events for
Insurance and Finance,
Springer-Verlag, Berlin (1997).
15th International Summer School 1999 of the
Swiss Association of Actuaries
Modelling Extremal Events
for Insurance and Finance
Ecole d'été des associations d'actuaires des pays des
communautés européennes
ISA,
Ecole des
HEC,
University of Lausanne, August 9-13,
1999
Lecturers:
Course outline:
- An overview of extreme value theory (EVT) will be given. The
newly introduced methodology is exemplified via S-Plus software programs
specially written for this purpose.
- The EVT results are used to complement existing risk management
(RM) techniques in finance and insurance. After giving an overview of
current best practice in RM, we discuss the ways in which EVT offers a
useful tool to go beyond the existing measures, such as Value-at-Risk
(VaR). Various examples based on data from insurance and finance are
given.
- We also discuss the necessary RM methodology underlying an
Integrated Risk Management System (the integration standing for
underwriting as well as investment risk). The usefulness for finance of
classical acturial tools will be highlighted.
- Some common caveats based on the use of correlation in finance
and insurance will be presented.
Course text:
P. Embrechts, C. Klüppelberg
and T. Mikosch:
Modelling Extremal Events for
Insurance and Finance,
Springer-Verlag, Berlin (1997).
[Top] [Finance and Insurance][MAS Finance][RiskLab][Department of Mathematics][ETH Zürich]