|
|
INHALT & PFAD:
|
Für den Fall, dass Ihr Computer das entsprechende Format nicht angezeigen kann, können Sie sich hier das Dokument als unformatierte Textausgabe ansehen.
(Bitte haben Sie dafür Verständnis, dass gewisse Dokumente nicht als Textalternative zur Verfügung stehen.)
|
|
Oldenburger Einladung zum Mathe-Kolloquium am 14.4.10
|
Fulltext:
Vortrag im Rahmen des
Mathematisches
Kolloquium
Institut für Mathematik
14. April 2010
mathematischen Kolloquiums:
Dr. Katrien Antonio
(University of Amsterdam)
Micro-level stochastic loss reserving
Abstract: In this talk we discuss the use of microlevel stochastic
models for the runoff of insurance claims. Our analysis uses policy
exposure, claims and payments experience data from real life insurance
portfolios. Modeling the runoff of both Reported But Not Settled
(RBNS) and Incurred But Not Reported (IBNR) claims is the very aim of
our work. We put focus on the following components of the
development process: the reporting delay, the time to an event, the
conditional event type, the conditional payment type (if any), and the
conditional severity (if any). We distinguish three types of events:
settlement without payment, settlement with a payment and a
payment without settlement. Given that a payment is to be made, the
conditional payment type model describes the probability that it will be
one of three claim types, or any possible combination of them. The
conditional severity component describes the claim amount structure
according to the combination of types paid. We provide appropriate
statistical models for each component and calibrate them to the
available data. Our approach is in line with the intensitybased
approach in Haastrup and Arjas (1996) but is adapted to the specific
hierarchical structure of our data. Our intention is to illustrate the close
connection between the actuarial problem of individual claims
development in nonlife insurance and the statistical framework of
recurrent events. Cook and Lawless (2007) provides a recent overview
of statistical techniques for the analysis of this type of data. We
calculate reserves with this microlevel model and compare them with
reserve calculations obtained with traditional actuarial techniques (like
chainladder and stochastic models using generalized linear models).
References
R. Cook and J. Lawless. The statistical analyses of recurrent events.
Springer, New York, 2007.
S. Haastrup and E. Arjas. Claims reserving in continuous time: a
nonparametric Bayesian approach. ASTIN Bulletin, 26(2):139164, 1996.
Ort: Universität Oldenburg
Standort Wechloy
(Carl-von-Ossietzky-Straße)
Raum W1 0-006
Zeit: Mittwoch, den 14.04.2010,
17 Uhr c.t.
Kaffee/Tee 16.45 Uhr im Raum
W1 2-213
Zu dieser Veranstaltung laden wir Sie herzlich ein.
Oldenburg-Invitation to the Math-Coloquium at 4/14/10
Oldenburger Einladung zum Mathe-Kolloquium am 14.4.10
|
|
|
|
Textformat
Seitenanfang
-
Impressum
