Mortality projections for non-converging groups of populations

Abstract

We propose a nested multi-population mortality projection model in which the forces of mortality are modelled via an extended version of the Cairns-Blake-Dowd (CBD) model, and the resulting model parameters are forecast using a Vector Error Correction Model (VECM). Dependencies between different populations are accounted for by both cross-correlation and cointegration terms. The hierarchical set-up is flexible, easily interpretable, and leads to biologically plausible joint forecasts for middle and higher ages. Bayesian model estimation assures coherent forecasts and allows for quantifying the underlying joint uncertainty. We study two European empirical examples which suggest that -- contrary to the commonly stated convergence of mortality patterns -- significant differences seem to be an inherent feature in multi-national mortality. This calls for a modelling that does not enforce convergence through strict a priori assumptions.