Description: In this paper, we study a survival regression model known as Cox's proportional Hazards model. We assume that the data available are already grouped and develop a minimum distance estimation procedure that is also applicable when the data are also left or right censored. Asymptotic properties of the estimators are established and the numerical implementation of the method based on an iterated reweighted least squares algorithm is discussed.

Description: After reading the Panjer-Bellhouse paper in the Proceedings of the Ball State University Conference, I wondered whether their technique could be used when a realistic investment process was assumed. I believe that such an extension is necessary if the theory is to have any practical application I have had little success in trying to do this. I have decided to present some thoughts and to invite others with different perspectives to bring them to fruition.

Description: This is authors' Fellowship Credit Research Paper. This paper will develop a model for cash flow testing traditional participating insurance that utilizes pricing tools and assumptions to project reserve liabilities. The model makes use of finance and accounting tools to monitor the reasonableness of ending and intermediate surplus results that emerge under the various interest rate scenarios imposed.

Description: The conventional way to analyze grouped observations on a single variable is to construct histograms or, sometimes, fit a normal distribution. We extend this latter approach by allowing for transformations to near normality.

Description: In this paper we shall present our results in terms of the estimation of human mortality rates, but the results carry over to other applications. We shall discuss a Bayesian model that encompasses both graduation [smoothing] and prediction.

Description: This paper addresses the classification of products according to their accounting standards: SFAS 60 for traditional products, SFAS 97 for interest sensitive products, and SOP 95-1 for participating products. In particular, the question of which products should be classified under the Statement of Position will be addressed. In addition, it will be shown that if a product's dividend formula passes on to the policyholder significantly less than a full asset share an over-reserving problem will occur if the Statement of Position is used as the accounting system.

Description: Given a financial transaction we are often interested in the number of internal rates of return [yield rates] and their location. From an actuarial point of view, the fundamental question is to identify those transactions with a single yield rate, or a single rate in some interval such as the positive reals. In this paper we are concerned with this counting problem. We survey various results concerning this problem, and provide a unifying approach together with some new insights.

Description: This is a sequel to author's earlier paper on Installment Premiums. This paper explores the parallel case of apportionable premiums, another situation in which a special adjustment payment at death causes an otherwise somewhat complex policy to be identical with a more simple and familiar one. As with installment premiums, this will result in terminal reserves for the complex policy being exactly equal to those for its corresponding familiar policy.

Description: This paper is a sequel to Shapiro et. al. in that it discusses a similar role for CAI in topics specific to the text Actuarial Mathematics, by Bowers et. al 1986. The topics covered are the previous topics of actuarial notation, basic concepts, and what-if analysis, along with some new ideas for the presentation of stochastic models.

Description: Users of statistical packages should be more aware of the influence that outlying data points can have on their statistical analyses. Robust procedures provide formal methods to spot these outliers and reduce their influence. While a few robust procedures are mentioned in this article, one is emphasized and it is motivated by maximum likelihood estimation to make it seem more natural. In this article, the author will try to provide some background, beginning with maximum likelihood estimation of one parameter, that will hopefully make robust estimation seem natural and rather easy.