Description: Using data from the Mexican Social Security Institute for labor risks, this paper classifies the severity of sequels in three categories: mild, moderate and high, and attempts to relate this level with the characteristics of the worker and his activities at work. Toward this goal, a model was built using a multilogistic regression, which allowed predicting the severity of physical sequels caused by a labor risk. From Actuarial Research Clearing House, 2006.

Description: This paper derives limited fluctuations credibility results for the Generalized Linear Model GLM and the extended case of generalized linear mixed model GLMM. It shows how credibility depends on the sample size, the distribution of covariates, and the link function. This provides a mechanism to obtain confidence intervals for the GLM and GLMM estimators.

Description: These are the slides that go with the paper 'Mortality Modeling using Projection Pursuit Regression.' In that paper, the authors develop sixteen separate mortality models based on the current SOA mortality data being used for the preferred life study. The models are constructed using projection pursuit regression. The sixteen models arise from all combinations of sex, smoker status, select and ultimate status, and per life vs. per dollar mortality rates. In general the models confirm the following four facts: 1 Mortality rates increase as attained age increases. 2 Mortality rates increase as duration increases. 3 Mortality rates decrease as Face Amount Bands increase. 4. Mortality rates decrease if preferred underwriting is present.

Description: This paper develops a formal framework to model the behavior of individual and small group health insurance policies in a competitive market. In this framework, anti-selective lapse is not assumed, but arises as a result of rational consumers seeking the best value in a competitive market where the premium rates are restricted by law. The authors obtain a model that addresses a number of fundamental questions which have not been fully answered previously, including the effect of price-induced anti-selective lapse on the mix of insureds in a block and the optimal renewal price to maximize the aggregate profit of a block.

Description: A statistical estimate is obtained for the total number of nodes in a three level tree. The number of nodes at each level is randomly distributed with certain pattern of distribution. Then the result is applied to the problem of estimating the LRA [logical record access] in data base design in a more refined way. It is more refined in the sense of using more information contained in the empirical distributions and being associated with a probability statement.

Description: This paper critiques and supplements Professor Schuette's 'Linear Programming Approach to Graduation.' The main points are: 1. The graduation is a problem of estimating the mean vector of a multivariate variable under certain assumptions. Schuette and other discussants emphasized the robustness property of their proposed estimation. This paper points out their mistake and suggests some correcting directions based on Bayesian theory. 2. This paper provides a more complete theoretical rationale for the parameter choosing in the graduation problem. 3. This paper points out the incompleteness of a theorem's proof in Schuette's paper and supplements some interpretations and mathematical details for the proof of some other theorems from a different viewpoint.

Description: The prediction of adequate claims reserves is a major subject in actuarial practice and science. Due to their simplicity, the chain ladder [CL] and Bornhuetter-Ferguson [BF] methods are the most commonly used claims reserving methods in practice. This presentation develops an estimator for the conditional mean square error of prediction [MSEP] of the ultimate claim in the BF method. This will be done in the framework of generalized linear models [GLM] using the overdispersed Poisson model motivation for the use of CL factor estimates in the estimation of the claims development pattern.

Description: This abstract describes a paper that considers various specifications of the general discrete time risk model in which a serial dependence structure is introduced between the claims for each period.

Description: A key concept in post-retirement planning is the random variable future lifetime of a life aged x. While age is an important factor in the determination of this variable, there are other relevant factors, like the state of health and the character of a life aged x. The purpose of this article is to presents some preliminary observations regarding the conceptualization of future lifetime as a fuzzy random variable.