Description: Presentation at the 41st Actuarial Research Conference held on August 10-12, 2006 in Montreal, QC. This paper considers the problem of extending regime-switching models for asset returns to the situation with multiple asset markets. The conditional tail expectation CTE is highly sensitive to the assumed dependence structure between the regime models for the different markets. A Monte Carlo simulation is used to illustrate the cost of misspecification. The authors find that the model most commonly used by practitioners is worse than all of the alternatives that they investigate.

Description: Several previous papers treat the rate of interest as a stochastic process in the determination of values of insurances and annuity functions. None of these papers consider the current interest rate as a starting point in the model. In this paper, autoregressive interest models, which are conditional upon current and past interest rates, are developed. It is shown how these models may be applied to the evaluation of moments of interest, insurance and annuity functions. Numerical results are also given.

Description: This paper introduces a rich stochastic modeling framework for understanding risks in multiple-decrement contracts. The example in the paper is a 20-year Term insurance contract. Not only are mortality and lapsation considered stochastic, but the parameters governing them are. For example, mortality risk is composed of four risk elements, including error generated in the underwriting process, volatility around the best estimate, catastrophic events that impact mortality, and the trend in mortality improvement or deterioration. When stochastically modeled, the relative contribution and risk profile of each risk element can be evaluated. Generating stochastic mortality results provides a distribution of results that an organization faces and the severity and incidence of the tail events.

Description: We consider Libor market model and calibration process. We estimate some interest rate derivatives such as Caps and Swaptions. We use Monte Carlo methods with appropriate dynamics under spot measure and forward measure. Imposing martingale discretization property, the same quantities are estimated again to see a contrast or discrepancy in light of confidence interval. Based on algorithms discussed in the paper, “Arbitrage-free discretizations of lognormal forward Libor and swap rate models” by Glasserman, P and Zhao, X 2000, the algorithms are implemented in excel VBA. Starting with current market data such as FRAs and Bond Prices, we describe steps involved to estimate the price of interest rate derivatives such as Caps and Swaptions, which would be beneficial to the practitioners in the industry.

Description: The series expansion of a probability density function, known to actuaries by Esscher's name and to statisticians as the saddlepoint approximation, typically gets integrated to approximate probability values under the density, with a location parameter in the expansion chosen to optimize convergence of the integrated series. We review the general form, the accuracy and the derivation of the Esscher approximation. Then we propose using related series expansions for the derivative of a probability density function to approximate the value of the point of maximum likelihood for the density. The key is to make the value of the location parameter an unknown and assume it to be the point of maximum likelihood, which leads to a tractable optimization problem to find its value.

Description: Presentation from the 41st Actuarial Research Conference held on August 10-12, 2006 in Montreal, Canada. Fuzzy set theory is incorporated into times series analysis, giving fuzzy parameter estimates of models such as ARMA and GARCH. Examples are given, including returns on a stock and option valuation.

Description: In this paper, a mathematical model is constructed to study the deviations of claims, investment performance, operating expenses, and lapse expenses as random stochastic processes. Discussions of the paper submitted by 2 readers follows

Description: Describes using the new multi-risk scenario generator to create sensitivity tests at moderately adverse probability levels, resulting in margins to use for PBR.

Description: The CSTEP 'Cluster Sampling for Tail Estimation of Probability' system is a desktop-based application to assist actuaries in efficient stochastic modeling through the implementation of Representative Scenario approaches. Its goal is to provide actuaries with an open-source HPC 'High Performance Computation' research platform to select a sample set of representative 'pivot' risk scenarios through user-specified or user-researched distance definitions.

Description: This session covers stochastic modeling processes currently in use and explores others that may be beneficial to health actuaries. From the Record of the Society of Actuaries, Vol. 31, No. 2, Session 76