Abstract

Accurate modeling of mortality at advanced ages is crucial to the valuation of pension plans and life annuities, especially longevity annuities for which annuity payments start very late in life, say age 85. Parametric regression models extrapolate lifetime distribution to the advanced ages but do not guarantee goodness fit. Threshold life tables offer an alternative solution to this problem using piecewise distribution via the peaks-over-threshold approach in the extreme value family. However, parameter estimation of this model is challenging, especially the determination of the threshold. Regular estimation methods do not guarantee a smooth life table. In this research, we impose parameter constraints to achieve a smooth threshold life table and propose a Bayesian approach to obtain Bayes estimates of the parameters and approximate predictive density via simulation, which can be used to compute life expectancy and other measures of interest in a Bayesian framework.

Full Text
Published version (Free)

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 call