<![CDATA[Risk classification is the process of statistical modeling that classifies risks into cross-classified classes, characterized bythe rating factors. In this paper, risk classification is applied to estimate claim frequency rates, expressed in terms of claimcount per exposure unit. The Poisson regression model has been widely used to analyze claim frequency rates in the recentyears. However, under the Poisson model, the mean and variance is assumed to be equal within classes, i.e., homogeneousrates. In this paper, the Negative Binomial regression model is suggested to deal with heterogeneous rates. In addition, themeasures for goodness-of-fit of the model, namely the Pearson chi-square, deviance, and likelihood ratio test, are alsodiscussed. Finally, the procedure for estimation of parameters, namely the Iteratively Weighted Least Squares (IWLS), isalso shown. In this paper, the models are fitted and tested on two types of claim data; Canadian private automobile liabilityinsurance and Malaysian private automobile own damage insurance.]]>
Copyrights © 2004
