Mortality and life expectancy forecasting for a group of populations in developed countries: A multilevel functional data method

TL;DR

This paper introduces a multilevel functional data method for forecasting age-specific mortality across multiple populations in developed countries, leveraging principal component analysis to capture common and residual trends, and compares its accuracy with existing methods.

Contribution

The paper develops a novel multilevel functional data approach for mortality forecasting that accounts for population-specific residual trends and demonstrates its superior accuracy over existing methods.

Findings

The method outperforms other coherent methods in age-specific mortality forecasts.

It achieves comparable or better accuracy in life expectancy forecasts, with some limitations.

Convergence in forecasts can be achieved for certain populations, such as by sex and state in Australia.

Abstract

A multilevel functional data method is adapted for forecasting age-specific mortality for two or more populations in developed countries with high-quality vital registration systems. It uses multilevel functional principal component analysis of aggregate and population-specific data to extract the common trend and population-specific residual trend among populations. If the forecasts of population-specific residual trends do not show a long-term trend, then convergence in forecasts may be achieved. This method is first applied to age- and sex-specific data for the United Kingdom, and its forecast accuracy is then further compared with several existing methods, including independent functional data and product-ratio methods, through a multi-country comparison. The proposed method is also demonstrated by age-, sex- and state-specific data in Australia, where the convergence in forecasts can possibly be achieved by sex and state. For forecasting age-specific mortality, the multilevel functional data method is more accurate than the other coherent methods considered. For forecasting female life expectancy at birth, the multilevel functional data method is outperformed by the Bayesian method of \cite{RLG14}. For forecasting male life expectancy at birth, the multilevel functional data method performs better than the Bayesian methods in terms of point forecasts, but less well in terms of interval forecasts. Supplementary materials for this article are available online.