Loading...
Publication
Modeling non-life insurance price for risk without historical information
| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 628.15 KB | Adobe PDF |
Advisor(s)
Abstract(s)
How should an insurer price a risk for which there is no history? This work intends
to show, step by step, which main mechanisms are needed to capture the tariff model
of another insurance company minimizing the risk involved. The document generally deals with the price-making mechanisms in non-life insurance through the GLM
regression models — Generalized Linear Model, more precisely the Poisson, Gamma
and Tweedie models. Given the complexity of the application of these models in
experimental design, it is studied a simpler way to characterize the rate, namely considering the Box–Cox transformation with SUR — Seemingly Unrelated Regression.
An orthogonal experimental design to collect information is also presented as well as
an application of these methods in the motor industry considering different companies.
Description
Keywords
Pricing (non-life insurance) GLM Box–Cox Optimal designs SUR — Seemingly Unrelated Regression
Citation
Publisher
INE