Volume 37 - Article 17 | Pages 527–566  

Coherent forecasts of mortality with compositional data analysis

By Marie-Pier Bergeron-Boucher, Vladimir Canudas-Romo, James E. Oeppen, James W. Vaupel


Background: Mortality trends for subpopulations, e.g., countries in a region or provinces in a country, tend to change similarly over time. However, when forecasting subpopulations independently, the forecast mortality trends often diverge. These divergent trends emerge from an inability of different forecast models to offer population-specific forecasts that are consistent with one another. Nondivergent forecasts between similar populations are often referred to as "coherent."

Methods: We propose a new forecasting method that addresses the coherence problem for subpopulations, based on Compositional Data Analysis (CoDa) of the life table distribution of deaths. We adapt existing coherent and noncoherent forecasting models to CoDa and compare their results.

Results: We apply our coherent method to the female mortality of 15 Western European countries and show that our proposed strategy would have improved the forecast accuracy for many of the selected countries. The results also show that the CoDa adaptation of commonly used models allows the rates of mortality improvements (RMIs) to change over time.

Contribution: This study opens a discussion about the use of age-specific mortality indicators other than death rates to forecast mortality. The results show that the use of life table deaths and CoDa leads to less biased forecasts than more commonly used forecasting models based on the extrapolation of death rates. To the authors’ knowledge, the present study is the first attempt to forecast coherently the distribution of deaths of many populations.

Author's Affiliation

Other articles by the same author/authors in Demographic Research

The impact of the choice of life table statistics when forecasting mortality
Volume 41 - Article 43

Outsurvival as a measure of the inequality of lifespans between two populations
Volume 44 - Article 35

Decomposing changes in life expectancy: Compression versus shifting mortality
Volume 33 - Article 14

The Gompertz force of mortality in terms of the modal age at death
Volume 32 - Article 36

Decomposing demographic change into direct vs. compositional components
Volume 7 - Article 1

Subnational contribution to life expectancy and life span variation changes: Evidence from the United States
Volume 50 - Article 22

Longevity à la mode: A discretized derivative tests method for accurate estimation of the adult modal age at death
Volume 50 - Article 11

Variable-r in sex ratios: Formulas in honor of Jim Vaupel
Volume 49 - Article 26

Comparative evidence of years lived with reproductive-age morbidity in sub-Saharan Africa (2010‒2019)
Volume 49 - Article 6

The role of reductions in old-age mortality in old-age population growth
Volume 44 - Article 44

Onset of the old-age gender gap in survival
Volume 42 - Article 25

The threshold age of the lifetable entropy
Volume 41 - Article 4

Life lived and left: Estimating age-specific survival in stable populations with unknown ages
Volume 39 - Article 37

Expected years ever married
Volume 38 - Article 47

In Memoriam: Professor Jan M. Hoem
Volume 36 - Article 24

Demographic characteristics of Sardinian centenarian genealogies: Preliminary results of the AKeA2 study
Volume 32 - Article 37

Maternal longevity is associated with lower infant mortality
Volume 31 - Article 42

Unobserved population heterogeneity: A review of formal relationships
Volume 31 - Article 22

Cause-specific measures of life years lost
Volume 29 - Article 41

The difference between alternative averages
Volume 27 - Article 15

The crossover between life expectancies at birth and at age one: The imbalance in the life table
Volume 24 - Article 4

Attrition in heterogeneous cohorts
Volume 23 - Article 26

Senescence vs. sustenance: Evolutionary-demographic models of aging
Volume 23 - Article 23

Total daily change with age equals average lifetime change
Volume 22 - Article 36

No consistent effects of prenatal or neonatal exposure to Spanish flu on late-life mortality in 24 developed countries
Volume 22 - Article 20

Survival as a Function of Life Expectancy
Volume 21 - Article 29

The age separating early deaths from late deaths
Volume 20 - Article 29

Life lived and left: Carey’s equality
Volume 20 - Article 3

Formal Relationships: Introduction and Orientation
Volume 20 - Article 1

An integrated approach to cause-of-death analysis: cause-deleted life tables and decompositions of life expectancy
Volume 19 - Article 35

The modal age at death and the shifting mortality hypothesis
Volume 19 - Article 30

The relative tail of longevity and the mean remaining lifetime
Volume 14 - Article 7

Lifesaving, lifetimes and lifetables
Volume 13 - Article 24

Changing mortality and average cohort life expectancy
Volume 13 - Article 5

Age-specific contributions to changes in the period and cohort life expectancy
Volume 13 - Article 3

Oldest Old Mortality in China
Volume 8 - Article 7

Life Expectancy at Current Rates vs. Current Conditions: A Reflexion Stimulated by Bongaarts and Feeney’s "How Long Do We Live?"
Volume 7 - Article 8

Dr. Väinö Kannisto: A Reflexion
Volume 6 - Article 5

Most recent similar articles in Demographic Research

Standardized mean age at death (MADstd): Exploring its potentials as a measure of human longevity
Volume 50 - Article 30    | Keywords: formal demography, life expectancy, mean age at death, mortality, standardization

Mortality modelling with arrival of additional year of mortality data: Calibration and forecasting
Volume 50 - Article 28    | Keywords: Lee-Carter model, longevity risk reduction

How lifespan and life years lost equate to unity
Volume 50 - Article 24    | Keywords: life expectancy, life table entropy, life years lost, lifespan variation

Subnational contribution to life expectancy and life span variation changes: Evidence from the United States
Volume 50 - Article 22    | Keywords: decomposition methods, life expectancy, lifespan variation, subnational mortality

Mortality inequalities at retirement age between migrants and non-migrants in Denmark and Sweden
Volume 50 - Article 18    | Keywords: immigration, life expectancy, lifespan inequality, Nordic countries, pension age, pension policy