Multi-population Mortality Projection: The Augmented Common Factor Model with Structural Breaks

International Journal of Forecasting, Volume 39, Issue 1, pp 450-469, January–March 2023, DOI: 10.1016/j.ijforecast.2021.12.002

61 Pages Posted: 23 Jun 2020 Last revised: 13 Jan 2023

See all articles by PENGJIE WANG

PENGJIE WANG

Monash University

Athanasios A. Pantelous

Monash University - Department of Econometrics & Business Statistics

Farshid Vahid

Monash University - Department of Econometrics and Business Statistics

Date Written: October 9, 2020

Abstract

Multi-population mortality forecasting has become an increasingly important area in actuarial science and demography, as a means to avoid long-run divergence in mortality projection. This paper aims to establish a unified state-space Bayesian framework to model, estimate and forecast mortality rates in a multi-population context. In this regard, we reformulate the augmented common factor model to account for structural breaks in the mortality indexes. Further, we conduct a Bayesian analysis to make inferences and generate forecasts so that process, parameter and model uncertainties can be considered simultaneously and appropriately. The square-root-form of the Kalman Filter is exploited to improve robustness when sampling latent states. We illustrate the efficiency of our methodology through two distinctive case studies. The first uses Australian two-gender mortality data. The second projects mortality for a list of selected Eurozone countries, where the hierarchical clustering approach on principal components is utilised to group countries with similar mortality characteristics together. Both point and probabilistic forecast evaluations are considered in the empirical analysis. The derived results support the fact that the incorporation of stochastic drifts mitigates the impact of the structural change in the time indexes on mortality projection.

Keywords: Multi-population mortality projection; Augmented Common Factor (ACF) model; Structural change; Bayesian statistics

JEL Classification: G22; J11; C11; C51; C53

Suggested Citation

WANG, PENGJIE and Pantelous, Athanasios A. and Vahid, Farshid, Multi-population Mortality Projection: The Augmented Common Factor Model with Structural Breaks (October 9, 2020). International Journal of Forecasting, Volume 39, Issue 1, pp 450-469, January–March 2023, DOI: 10.1016/j.ijforecast.2021.12.002, Available at SSRN: https://ssrn.com/abstract=3614333 or http://dx.doi.org/10.2139/ssrn.3614333

PENGJIE WANG

Monash University ( email )

23 Innovation Walk
Wellington Road
Clayton, Victoria 3800
Australia

Athanasios A. Pantelous (Contact Author)

Monash University - Department of Econometrics & Business Statistics ( email )

Wellington Road
Clayton, Victoria 3168
Australia

Farshid Vahid

Monash University - Department of Econometrics and Business Statistics ( email )

Wellington Road
Clayton, Victoria 3168
Australia
+61 3 9905 2359 (Phone)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
125
Abstract Views
573
Rank
344,255
PlumX Metrics