Modeling Non-Life Insurance Price for Risk without Historical Information

Authors

  • Filipe Charters de Azevedo Universidade Aberta
  • Teresa A. Oliveira Universidade Aberta
  • Amilcar Oliveira Universidade Aberta

DOI:

https://doi.org/10.57805/revstat.v14i2.185

Keywords:

pricing (non-life insurance), GLM, Box–Cox, optimal designs, SUR-Seemingly Unrelated Regression

Abstract

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.

Published

2016-04-20

How to Cite

Charters de Azevedo , F., A. Oliveira, T., & Oliveira , A. (2016). Modeling Non-Life Insurance Price for Risk without Historical Information. REVSTAT-Statistical Journal, 14(2), 171–192. https://doi.org/10.57805/revstat.v14i2.185