الفهرس | Only 14 pages are availabe for public view |
Abstract This research focuses on the problem of ratemaking for group health insurance policies. The problem is addressed from both: (1) a theoretical perspective, where the main relevant theories and models are reviewed in order to select the most suitable modeling approach; and (2) an empirical perspective, where a real dataset from the Egyptian insurance market is used to illustrate the application of the proposed methodology. The spectrum of models considered in this research ranged from single level general linear models (including both cross-sectional, and pooled cross-sectional models) up to panel/longitudinal multilevel (cross-classified) models. This helped to illustrate the additional gains achieved by using these more advanced models. It also showed how they can be used to allow for the special features of group health insurance policies and its related modeling complexities & data challenges. All results were confirmed through both in-sample goodness of fit tests and out-of- sample validation. |