State Space Vasicek Model of a Longevity Bond

TL;DR

This paper introduces a novel state-space Vasicek model for pricing zero coupon longevity bonds, incorporating financial and mortality risks, and uses Kalman filtering for empirical estimation based on U.S. Treasury data.

Contribution

It presents a new affine Vasicek model in a state-space form for longevity bonds, integrating interest rate and mortality risk with uncorrelated noises, and demonstrates its empirical applicability.

Findings

Interest rate exhibits mean reversion in U.S. term structure

Model fits well with historical mortality and yield data

Simulation of survival rates enables longevity risk modeling

Abstract

Life expectancy have been increasing over the past years due to better health care, feeding and conducive environment. To manage future uncertainty related to life expectancy, various insurance institutions have resolved to come up with financial instruments that are indexed-linked to the longevity of the population. These new instrument is known as longevity bonds. In this article, we present a novel classical Vasicek one factor affine model in modelling zero coupon longevity bond price (ZCLBP) with financial and mortality risk. The interest rate r(t) and the stochastic mortality of the constructed model are dependent but with uncorrelated driving noises. The model is presented in a linear state-space representation of the contiuous-time infinite horizon and used Kalman filter for its estimation. The appropriate state equation and measurement equation derived from our model is used as a method of pricing a longevity bond in a financial market. The empirical analysis results show that the unobserved instantaneous interest rate shows a mean reverting behaviour in the U.S. term structure. The zero-coupon bonds yields are used as inputs for the estimation process. The results of the analysis are gotten from the monthly observations of U.S. Treasury zero coupon bonds from December, 1992 to January, 1993. The empirical evidence indicates that to model properly the historical mortality trends at different ages, both the survival rate and the yield data are needed to achieve a satisfactory empirical fit over the zero coupon longevity bond term structure. The dynamics of the resulting model allowed us to perform simulation on the survival rates, which enables us to model longevity risk.