Modelling mortality: A bayesian factor-augmented var (favar) approach

Abstract Longevity risk is putting more and financial pressure on governments pension plans worldwide due to pensioners’ increasing trend of life expectancy the growing numbers people reaching retirement age. Lee Carter (1992, Journal American Statistical Association , 87 (419), 659–671.) applied a one-factor dynamic factor model forecast mortality improvement, has since become field’s workhorse. It is, however, well known that their subject limitation overlooking cross-dependence between different age groups. We introduce Factor-Augmented Vector Autoregressive (FAVAR) models modelling literature. The model, obtained by adding an unobserved process (VAR) process, nests VAR Lee–Carter as special cases inherits both frameworks’ advantages. A Bayesian estimation approach, adapted from Minnesota prior, proposed. empirical application US French data demonstrates our proposed method’s efficacy in in-sample out-of-sample performance.