Description: This paper addresses some pervasive problems in using secondary data in actuarial research. An approach to solving these problems is based on information theory. From Transactions of Society of Actuaries 1995, Vol. 47.

Description: Abstracts of various papers published in ARCH 1983 Vol. 1

Description: This paper presents a statistical methodology based upon information theory, for adjusting mortality tables to obtain exactly some known individual characteristics, while obtaining a table that is as close as possible to a standard one. Followed by a discussion paper submitted

Description: Since the world in which actuaries work is both expanding (through 'data science' opportunities) and contracting (since 'data scientists' are doing work formerly done by actuaries), the role of education actuaries is at a tipping point. Members of the Society who are in higher education and representatives from the business community will discuss ways in which the two worlds of business and education have worked together in the past, what can be done by each group to assist the other, and what the future may hold.

Description: Discussion of how to obtain tight upper and lower bounds on E[hX] for a given function h, and a random variable X with three known moments.

Description: Shows how to use personal information such as medical history, family characteristics, etc. in a logical statistical fashion for the purpose of modifying an existing mortality table to reflect the collected underwriting information.

Description: This abstract describes a paper that shows that by modeling the time series of mortality rate changes rather than mortality rate levels, human mortality can be better modeled.

Description: This paper presents a unifying non-Bayesian statistical method for incorporating prior information into the determination of probability distributions and other finite measures and develops the statistical properties of this method together with actuarial applications. A discussion of the paper follows. From Transactions of Society of Actuaries 1991, Vol. 43.

Description: In this article, the authors introduce a new policy-making model for pension plan funding which openly represents the uncertainty. The word 'policy' is used here to indicate a strategy which is intended to be followed most [but not necessarily all] of the time. In unusual circumstances, the policy will have to be modified at the end of the year to retain qualification. However, the frequency with which this remedial action is needed is controllable by the actuary [unlike the method of using expected values]. The simple substitution of expected values of random quantities produces an unknown frequency of last minute remedial actions at possibly disastrous investment costs to the pension plan. However, with this paper's techniques, once the actuary acknowledges the uncertainty associated with the various aspects of the pension plan, he/she can explicitly trade off the costs associated with remedial actions, tax penalties, etc. with the investment returns in order to meet the pension plan goals. The method that this paper introduces is a new Chance-Constrained Programming approach to selecting annual contribution levels and asset allocation [holding other factors fixed] that the authors believe will better fit the employer's goals while recognizing the many risks and constraints associated with defined benefit plans. From Actuarial Research Clearing House 1993, Vol. 3.

Description: This paper describes methods for determining bounds on the price of derivative instruments, such as option on insurance futures, given only market information. From Securitization of Insurance Risk: The 1995 Bowles Symposium, M-FI97-1.