Volume 30 - Article 27 | Pages 795–822 Author has provided data and code for replicating results

Joint probabilistic projection of female and male life expectancy

By Adrian E. Raftery, Nevena Lalic, Patrick Gerland

Print this page  Facebook  Twitter


Date received:13 Mar 2012
Date published:14 Mar 2014
Word count:5629
Keywords:autoregressive model, Bayesian hierarchical model, oldest old, potential support ratio, t distribution, United Nations World Population Prospects
Additional files:readme.30-27 (text file, 801 Byte)
 demographic-research.30-27 (zip file, 2 kB)


Background: The United Nations (UN) produces population projections for all countries every two years. These are used by international organizations, governments, the private sector and researchers for policy planning, for monitoring development goals, as inputs to economic and environmental models, and for social and health research. The UN is considering producing fully probabilistic population projections, for which joint probabilistic projections of future female and male life expectancy at birth are needed.

Objective: We propose a methodology for obtaining joint probabilistic projections of female and male life expectancy at birth.

Methods: We first project female life expectancy using a one-sex method for probabilistic projection of life expectancy. We then project the gap between female and male life expectancy. We propose an autoregressive model for the gap in a future time period for a particular country, which is a function of female life expectancy and a t-distributed random perturbation. This method takes into account mortality data limitations, is comparable across countries, and accounts for shocks. We estimate all parameters based on life expectancy estimates for 1950-2010. The methods are implemented in the bayesLife and bayesPop R packages.

Results: We evaluated our model using out-of-sample projections for the period 1995-2010 and found that our method performed better than several possible alternatives.

Conclusions: We find that the average gap between female and male life expectancy has been increasing for female life expectancy below 75, and decreasing for female life expectancy above 75. Our projections of the gap are lower than the UN’s 2008 projections for most countries and thus lead to higher projections of male life expectancy.

Author's Affiliation

Adrian E. Raftery - University of Washington, United States of America [Email]
Nevena Lalic - University of Washington, United States of America [Email]
Patrick Gerland - United Nations, United States of America [Email]

Other articles by the same author/authors in Demographic Research

» Bayesian projection of life expectancy accounting for the HIV/AIDS epidemic
Volume 37 - Article 48

» Regional probabilistic fertility forecasting by modeling between-country correlations
Volume 30 - Article 35

» Old age mortality in Eastern and South-Eastern Asia
Volume 29 - Article 38

» Estimating trends in the total fertility rate with uncertainty using imperfect data: Examples from West Africa
Volume 26 - Article 15

» Hotspots and Coldspots: Household and village-level variation in orphanhood prevalence in rural Malawi
Volume 19 - Article 32

Most recent similar articles in Demographic Research

» Global estimation of neonatal mortality using a Bayesian hierarchical splines regression model
Volume 38 - Article 15    | Keywords: Bayesian hierarchical model

» Bayesian projection of life expectancy accounting for the HIV/AIDS epidemic
Volume 37 - Article 48    | Keywords: Bayesian hierarchical model

» Survival differences among the oldest old in Sardinia: who, what, where, and why?
Volume 14 - Article 13    | Keywords: oldest old

» Sociodemographic Effects on the Onset and Recovery of ADL Disability among Chinese Oldest-old
Volume 11 - Article 1    | Keywords: oldest old

» Old-Age Mortality in Germany prior to and after Reunification
Volume 3 - Article 1    | Keywords: oldest old