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: Presented at Living to 100 symposium, January 2002. This paper proposes a standard operating procedure for testing the Gompertz assumption using yearly age-specific mortality data, and the impacts of the data collection period and population sizes on the testing results are discussed.

Description: This paper employs a static-component projection methodology as a first step in a more complex research agenda focusing on developing detailed population projections in which mortality, disability, and disease are represented as linked phenomena with changes in any one impacting the other two. From Retirement Needs Framework, M-RS00-1.

Description: This article proposes a framework for estimating mortality improvement models and analyzing the parameter uncertainty in such models.

Description: Presented at Living to 100 Symposium, January 2011. This study adapts the idea of regular discount sequence in the bandit problem, and uses it to interpret life expectancy, as well as to develop a model for survival probabilities. Data came from multiple countries.

Description: Presented at Living to 100 Symposium, January 2011. This research studies coherent mortality modeling by combining a group of populations with similar period effects - e.g., mortality behaviors - in an effort to improve the stability of mortality modeling for older ages.

Description: 2011 Enterprise Risk Management Symposium, Chicago. This paper highlights the impact that a change in conditional data would have on a variety of risk assessment models, with specific emphasis on investment forecasting.