Description: The main objective of this study is to analyze and control a surplus dependent risk process, where larger surpluses allow for a wider underwriting policy. We focus here mostly on the diffusion approximation of the risk process. The results are derived in two papers Brownian motion in Risk Theory, submitted for publication, and Surplus dependent risk processes defined by stochastic differential equations, in preparation. We only include here a long summary of these papers.

Description: In this paper some general properties of compound nonstationary Poisson processes are discussed as well as the possible shapes of the intensity function. A decomposition of the accumulated claims as a sum of independent compound Poisson sums is shown. An embedded discrete risk model is introduced. It is shown that ruin probabilities and maximal losses for the nonstationary risk model find lower bounds with the embedded discrete model. From Actuarial Research Clearing House 1994 VOL. 1.

Description: This is the abstract of the paper 'A Stochastic Definition of Future Shares'. The traditional definition of actuarial future values and stochastic definition of Ramsay are discussed. A modification of Ramsay's definition is proposed and an application to life insurance reserves is presented.

Description: Two renewal processes, known in reliability maintenance as minimal repair and replacement policy, are introduced in this paper. Their properties are studied in the case where the generating random sequence has a distribution with periodic failure rate. Applications in risk theory are shown. From Actuarial Research Clearing House 1993, VOL. 1.

Description: In the paper, the authors implement the empirical version of a robust Kalman filter credibility estimator with a data set, and compare its sensitivity to large claims with that of other credibility estimators in the literature.

Description: The minimum distance estimator proposed allows for the selection of the best fitting family member without prior distributional assumptions. It is shown that this estimator is consistent and can be made either robust or asymptotically efficient. Its asymptotic distribution is derived and and illustrated with automobile insurance data. From the Actuarial Research Clearing House 1990 Vol. 1