Description: Investment Fallacies: Extended periods of robust macroeconomic growth are healthy for investing.

Description: Non-consequentiality is quite consequential for the claims made for the applicability of Risk Theory RT to decision problems that are not transparently tactical or wholly instrumental. On the negative side, RT is not normative or even a complete heuristic in such contexts. The author takes strong exception to the common tendencies, A to link risk theory with welfarism and versions of utilitarianism, and B to claim that with or without but especially with such linkage RT is normative in both moral and rational analysis, choice and action.

Description: Investment Fallacies: A real-world approach to Value at Risk

Description: Recent advances in mortality modeling have enabled applicant-specific quantification of mortality risk in life insurance applicants using laboratory and physical measurements. Relative to more conventional underwriting, this approach identifies a small population of significantly under-priced policy and a much larger, cross-subsidizing group whose risk is presently overestimated. Applicants placed in the highest percentile by this scoring methodology are more than 10X as likely to die in a given period as their demographic peers, and represent approximately 5% of short-term claims. Implications for product design are substantial in both the short- and long-term, as the possibilities for adverse selection grow, and the opportunity for fully individualized pricing raises the more distant prospect of products with as many rate classes as applicants.

Description: Is Risk/Return a sound tool for decision-making? No. It is not consistent, not objective, distorts decision and degrades governance. Why? What shall we do then?

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: Statistical properties of interest, annuity and insurance functions are examined when mortality and interest are treated as having a random component. Several special models of interest rate fluctuation are examined in detail. It is hoped that such theory will be useful in developing fluctuation reserves and premium margins. Presented at the 13th Annual Actuarial Research Conference, Ball State University, August 31st. September lst, 2nd. 1978.

Description: Discusses the influence of market-consistent pricing proponents.

Description: In this expository paper several comments are made with respect to the statistical independence of the curtate future lifetime and the fractional part of the future lifetime, both of a general status. In particular, the conditions for independence need to be stated carefully. The last-survivor status is cited as an example. More general assumptions than the uniform distribution of deaths assumption are then considered, together with applications to insurances, annuities, and reserves. Similar results to those under the uniform distribution of deaths assumption are obtained. Brief comments are made with respect to contingent probabilities in multiple lives and multiple decrement theory.

Description: This paper shows how discrete multivariate analysis or multidimensional contingency table methods may be applied to data arising in actuarial work. A brief introduction to the theory is followed by two detailed examples of its application. Finally, the concluding remarks indicate how the procedure could be incorporated into a complete rate-making procedure. This work was performed for the U.S. Department of Housing and Urban Development.