Results of a research project that explored the covariance and correlation among various insurance and non–insurance risks in the context of risk based capital. The project was particularly focused on the correlations of these risks under extreme conditions or as is sometimes termed "in the tail of the distribution."
The first phase of the project was a literature review to determine what work has already been done in this area and might be beneficial for the project. The completed literature search, in bibliography form, can be found at the following link
The objective of the second phase of the project was the development of an educational model for actuaries on the use of copulas for simulation of extreme events. The model was programmed into an Excel workbook using a simulation add–in. The Excel workbook and accompanying documentation can be obtained from the links below.
ABSTRACT. We describe a simple way to construct a bivariate copula with specified marginals and partially specified dependence. For example, our method
allows one to model tail behavior scenarios while holding the core of the joint distribution fixed. We provide an Excel workbook to illustrate the method, including its use in Monte Carlo simulation.