The Copula-Based Total Claim Amount Regression Model with an Unobserved Risk Factor
The Copula-Based Total Claim Amount Regression Model with an Unobserved Risk Factor

Summary/Abstract: Nowadays a common practice of any insurance company is ratemaking, which is defined as the process of classification of the mass risk portfolio into risk groups where the same premium corresponds to each risk. As generalised linear models are usually applied, the process requires the independence between the average value of claims and the number of claims. However, in literature this assumption is called into question. The interest of this paper is to propose the copula-based total claim amount model taking into account an unobservable risk factor in the claim frequency model. This factor, called also as unobserved heterogeneity, is treated as a random variable influencing the number of claims. The goal is to estimate the expected value of the product of two random variables: the average value of claims and the number of claims for a single risk assuming the dependence between the average value of claims and the number of claims for a single risk and the dependence between the number of claims for a single risk and the unobservable risk factor. We give details of the theoretical aspects of the model as well as the empirical example. To acquaint the reader with the model operation, every step of the process of the expected value estimation in described and the R code is available for download, see http://web.ue.katowice.pl/woali/.

• Details
• Contents