A NEW MULTIVARIATE ZERO-INFLATED HURDLE MODEL WITH APPLICATIONS IN AUTOMOBILE INSURANCE

Abstract The fact that a large proportion of insurance policyholders make no claims during one-year period highlights the importance zero-inflated count models when analyzing frequency claims. There is vast literature focused on univariate case models, while work in area multivariate considerably less advanced. Given companies write multiple lines business, where claim counts these business are often correlated, there strong incentive to analyze models. Motivated by idea Liu and Tian ( Computational Statistics Data Analysis , 83 200–222; 2015), we develop hurdle model describe data with extra zeros. This generalization offers more flexibility modeling behavior individual also incorporating correlation structure between for different business. We an application expectation–maximization (EM) algorithm enable statistical inference necessary estimate parameters associated our model. Our then applied automobile portfolio from major company Spain. demonstrate performance superior compared several alternatives.