Description: This paper develops credibility using a longitudinal data framework. In a longitudinal data framework, one might encounter data from a cross-section of risk classes towns with a history of insurance claims available for each risk class. For the marginal claims distributions, we use generalized linear models, an extension of linear regression that also encompasses Weibull and Gamma regressions. Copulas are used to model the dependencies over time specifically, this paper is the first to propose using a t-copula in the context of generalized linear models. The t-copula is the copula associated with the multivariate t-distribution like univariate t-distributions, it seems especially suitable for empirical work. Moreover, we show that the t-copula gives rise to easily computable predictive distributions that we use to generate credibility predictors. Like Bayesian methods, our copula credibility prediction methods allow us to provide an entire distribution of predicted claims, not just a point prediction.

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: This is the abstract of a paper that complements the existing research on optimal reinsurance by proposing another model for the determination of the optimal reinsurance design.

Description: When fitting a model to any data, there is some uncertainty about which model is best. Green [1995] quantifies this uncertainty through the Reversible Jump Markov Chain Monte Carlo [RJMCMC] method. When using the RJMCMC method in a regime-switching situation, the chain determines the optimal number of regimes by jumping between various possibilities. This method gives each model its posterior probability of being the best. After an overview of the methodology, the authors apply it to various datasets and discuss the applications in modern actuarial science.

Description: This is a stochastic model used to find the distribution of the discounted value of all future cash-flows.

Description: Many insurers preparing market consistent financial statements encounter the issue of developing volatility assumptions for equity options and guarantees that are longer than any observable market data. This presentation develops a generalization of the classical Black Scholes option pricing model that is consistent with the European CRO Forum's framework for valuing non-hedgeable risk. The presentation argues that, with reasonable parameter choices, the model fits observed volatility surfaces well enough that it can be used to estimate implied volatilities where no market data exists.

Description: This paper addresses the fuzziness in regression models. The goal is to present a test procedure to explicitly examine whether an independent variable has a clear functional relationship with the dependent variable in a specific regression model, or whether their relationship is fuzzy. To this end, the authors interpret the spread of the regression coefficients as a statistic measuring the fuzziness of the relationship between the corresponding independent variable and the dependent variable. They then derive test distributions based on the null hypothesis that such spreads could have been obtained with data generated by a classical regression model with random errors. The analysis is presented in conceptual rather than technical terms.

Description: This abstract describes a paper that introduces spatio-temporal models and methods for analysis with specific emphasis on quantities of interest in actuarial science. Generalized additive mixed models are used for the analysis of geographic and temporal variability of mortality rates.

Description: This abstract describes a paper that studies Gerber-Shiu functions and dividend payments in an insurance risk model driven by a spectrally negative Levy process of bounded variation.

Description: The theme of this paper relates to solving portfolio selection problems using linear programming. The authors extend the linear optimization framework for Conditional Value-at-Risk-based portfolio selection problems to optimization over a more general class of risk measure known as the class of Coherent Distortion Risk Measure. From Actuarial Research Clearing House, 2012 Vol. 1.