Sources of Distortion in Classification Ratemaking Data and Their Treatment

Classification ratemaking represents an important role of most actuaries. In order to increase stability when analyzing class relativities it is customary to combine the premium and loss experience of several years as well as from more than one state. This paper examines the possible distortions that may be introduced when such combinations are made. Two scaling factors are presented which address the distortion that has been detected. The paper then shifts focus to the impact of the distortion on methods presented in two important papers published in the Proceedings of the Casualty Actuarial Society.