Abstract

Journal of Actuarial Practice

Volume 12, 2005


Ultimate Ruin Probability for a Time-Series Risk Model with Dependent Classes of Insurance Business

Lai Mei Wan, Kam Chuen Yuen, and Wai Keung Li

Abstract

We consider a discrete-time risk model with m (m ≥ 2) dependent classes of insurance business. The claim processes of these m classes are assumed to follow a multivariate autoregressive time-series model of order 1. Given this claims model, we explore the probability of ultimate ruin assuming exponentially bounded claims. As an example, we use simulations to study the case where there are two business and the underlying losses are of two types: bivariate exponential and bivariate gamma claim distributions.

Key words and phrases: adjustment coefficient, bivariate exponential  distribution, bivariate gamma distribution, discrete-time risk model, multivariate autoregressive model, time series, ultimate ruin probability

Corresponding Author:

Kam C. Yuen

Department of Statistics and Actuarial Science,

University of Hong Kong, Pokfulam Road,

HONG KONG

E-mail: kcyuen@hku.hk


© Copyright Absalom Press, Inc.