Description: This paper considers the problem of parametric estimation of loss distributions in a very general context. It uses the minimum distance method with the Cramér-von Mises statistic as the particular choice of distance. The authors show how to compute the influence function for the estimator. They also use the influence function to obtain more information about the variance and the robustness of the estimator. They demonstrate, with an example, how much more resistant to contamination this estimator is compared with the more classical maximum likelihood estimator.

Description: Because actuaries fit models for a variety of situations, particularly with regard to data modifications, it is useful to have a single approach. Though not optimal or exact for a particular model or data structure, the method should be reasonable for most all settings. Such a method is proposed in this article. Actuarial Research Clearing House 2003, VOL. 1

Description: This article examines how parameter uncertainty leads to uncertainty in Value at Risk VaR estimates. Lacking a closed form solution, we use a first order approximation of VaR to map parameter changes into changes in the VaR value. When the asymptotic distribution of parameter estimates is normal, this implies a normal approximation of the confidence interval about VaR. We describe this approximation in detail and explore some extensions to risk factor modeling.

Description: In this paper, we study a survival regression model known as Cox's proportional Hazards model. We assume that the data available are already grouped and develop a minimum distance estimation procedure that is also applicable when the data are also left or right censored. Asymptotic properties of the estimators are established and the numerical implementation of the method based on an iterated reweighted least squares algorithm is discussed.