Date of Award


Document Type


Degree Name

Doctor of Philosophy (PhD)


School of Mathematical and Statistical Sciences

Committee Member

Yu-Bo Wang


The improvement of mortality projection is a pivotal topic in the diverse branches related to insurance, demography, and public health. The dissertation consists of two distinct but related projects about mortality projection. We consider hierarchical bilinear modeling, variable selection methods and spatio-temporal structure under Bayesian frameworks in the estimation of mortality rate for multiple populations.First, we propose a Bayesian model to estimate and predict mortality rates for multi-population, motivated by the thread of Lee-Carter related models. This new model features information borrowing among populations and properly reflecting variations of data. It also provides a solution to a long-time overlooked problem: model selection for dependence structures of population-specific time parameters. By introducing a Dirac spike function, simultaneous model selection and estimation for population-specific time effects can be achieved without much extra computation cost. Further, this work discusses a Bayesian probit model to provide a dependence structure involving spatial information together with the Dirac spike function. We use the Japanese mortality data from the Human Mortality Database to illustrate the desirable properties of our model. Second, this work develops Bayesian mortality projection models for multiple populations by considering the stochastic structure and the effect of spatial autocorrelation within the observations. We explain high levels of overdispersion according to adjacent regions based on the conditional autoregressive model. In an empirical study, this dissertation compares different hierarchical projection models for the analysis of geographical diversity in mortality among multiple Japanese counties in consecutive years, grouped by age. We implement Markov chain Monte Carlo (MCMC) computation to conduct parameter estimation. Results have demonstrated the flexibility and predictive performance of our proposed model.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.