Abstract
Although a large number of mortality projection models have been proposed in the literature, relatively little attention has been paid to a formal assessment of the effect of model uncertainty. In this paper, we construct a Bayesian framework for embedding more than one mortality projection model and utilise the finite mixture model concept to allow for the blending of model structures. Under this framework, the varying features of different model structures can be exploited jointly and coherently to have a more detailed description of the underlying mortality patterns. We show that the proposed Bayesian approach performs well in fitting and forecasting Japanese mortality.
Highlights
In the demographic, actuarial, and insurance literature, the two main branches of mortality projection models are the Lee and Carter (1992) model family and the Cairns et al.(2006) (CBD) model family
There have been a large number of their variations, extensions, and applications to date (e.g., Lee 2000; Cairns et al 2009; Haberman and Renshaw 2011). In most of these works, the selection of mortality projection models is mainly based on certain standard statistical criteria, such as the Akaike information criterion (AIC), Bayesian information criterion (BIC), mean square error (MSE), and mean absolute percentage error (MAPE)
We devise a Bayesian framework for integrating multiple mortality
Summary
Actuarial, and insurance literature, the two main branches of mortality projection models are the Lee and Carter (1992) model family and the Cairns et al. Once the “best model” is determined, the common practice is to apply the selected model singly to the problem under consideration (e.g., demographic projection, longevity risk pricing and hedging, capital assessment) While this approach is reasonably sound in its own right, it ignores the fact that there is still much uncertainty in how close the chosen model is to the true underlying mechanism and that the other suboptimal models may still capture useful aspects that are omitted by the selected model. The overall density function is expressed as a weighted average of the density functions of the individual components Another perspective of using a finite mixture model is to take it as a semi-parametric approach that provides a more flexible way for handling complex data patterns, in contrast to applying a single model with limited features.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
