Catastrophe modeling with a doubly stochastic process : Bayesian inference and applications
- This work proposes to employ the (bursty) GLO model from Bingmer et. al (2011) to model the occurrence of tropical cyclones. We develop a Bayesian framework to estimate the parameters of the model and, particularly, employ a Markov chain Monte Carlo algorithm. This also allows us to develop a forecasting framework for future events. Moreover, we assess the default probability of an insurance company that is exposed to claims that occur according to a GLO process and show that the model is able to substantially improve actuarial risk management if events occur in oscillatory bursts.
Author: | Christian KubitzaGND |
---|---|
URN: | urn:nbn:de:hebis:30:3-382988 |
Referee: | Gaby SchneiderGND, Anton WakolbingerGND |
Advisor: | Gaby Schneider |
Document Type: | Master's Thesis |
Language: | English |
Date of Publication (online): | 2015/10/13 |
Year of first Publication: | 2015 |
Publishing Institution: | Universitätsbibliothek Johann Christian Senckenberg |
Granting Institution: | Johann Wolfgang Goethe-Universität |
Date of final exam: | 2015/08/31 |
Release Date: | 2015/10/13 |
Tag: | Bayesian Inference; catastrophe modeling; doubly stochastic point process; poisson process; risk theory |
Page Number: | 120 |
Last Page: | 115 |
HeBIS-PPN: | 36532826X |
Institutes: | Informatik und Mathematik / Mathematik |
Dewey Decimal Classification: | 5 Naturwissenschaften und Mathematik / 51 Mathematik / 510 Mathematik |
Sammlungen: | Universitätspublikationen |
Licence (German): | Deutsches Urheberrecht |