Longevity Forecasting by Socio-Economic Groups Using Compositional Data Analysis

Kjærgaard, Søren; Ergemen, Yunus Emre; Bergeron-Boucher, Marie-Pier; Oeppen, Jim; Kallestrup‐Lamb, Malene

doi:10.1111/rssa.12555

Cited by 13 publications

(16 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4 The results are not identical because Figure 3 is based on smoothed rates to identify the main patterns. 5 A similar result is found by Kjaergaard et al (2020) for Danish males.…”

Section: Conflict Of Interestsupporting

confidence: 66%

See 1 more Smart Citation

Insight into stagnating adult life expectancy: Analyzing cause of death patterns across socioeconomic groups

2020

Self Cite

View full text Add to dashboard Cite

This study analyzes the complexity of female longevity improvements. As socioeconomic status is found to influence health and mortality, we partition all individuals, at each age in every year, into five socioeconomic groups based on an affluence measure that combine an individual's income and wealth. We identify the particular socioeconomic groups that have been driving the standstill for Danish females at older ages. Within each socioeconomic group, we further analyze the cause of death patterns. The decline in life expectancy for Danish females is present for four out of five subgroups, however, with particular large decreases for the low-middle and middle-affluence groups. Cancers, smoking-related lung and bronchus causes, and other diseases particularly contribute to the stagnation. For four of the five socioeconomic groups only small cardiovascular improvement are experienced during the period of stagnating life expectancy compared to an equally long and subsequent period.

show abstract

“…4 The results are not identical because Figure 3 is based on smoothed rates to identify the main patterns. 5 A similar result is found by Kjaergaard et al (2020) for Danish males.…”

Section: Conflict Of Interestsupporting

confidence: 66%

“…1 1 As this study analyze the stagnation period until around 1994 data for more recent years are not presented here, for more recent results see Kjærgaard, Ergemen, Bergeron Boucher, Oeppen, and KallestrupLamb (2020), which consider both Danish males and females. …”

mentioning

confidence: 99%

Insight into stagnating adult life expectancy: Analyzing cause of death patterns across socioeconomic groups

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Other alternative models have been proposed and could potentially increase accuracy and robustness. To cite only a few, they could comprise: forecasts of life expectancy directly, using a Bayesian approach (Raftery et al 2012) or using best-practice as a reference (Torri & Vaupel 2012; forecasting the ASRMI directly (Bohk-Ewald & Rau 2017); forecast by causes of death (Kjaergaard et al 2019); forecast based on a different indicator (Bergeron-Boucher et al 2017, Bergeron-Boucher et al 2019; forecast for cohorts (Rizzi et al 2021); forecast by socioeconomic groups (Kjaergaard et al 2020), etc. Testing all these models was, however, outside the scope of this paper.…”

Section: Discussionmentioning

confidence: 99%

Mortality forecasting at age 65 and above: an age-specific evaluation of the Lee-Carter model

Bergeron-Boucher

Kjærgaard

2021

Scandinavian Actuarial Journal

View full text Add to dashboard Cite

The Lee-Carter (LC) model has been recurrently used to forecast mortality, including by national statistical offices. This model has many advantages, but tends to underpredict life expectancy due to its assumption of constant age-specific response to the time index. Does this bias emerge from all ages or from specific ages only? In this paper, we aim to provide a more detailed evaluation of the model, by evaluating its accuracy, bias and robustness by age. Our analysis is based on 806 out-of-sample forecasts using various different fitting periods and forecast horizons. We focus on age 65 and above, as most deaths occur at older ages nowadays. We showed that the LC model is not fundamentally biased, but its main assumption of constant age-specific response to the time index, often leading to constant rates of mortality improvement, is not appropriate in all populations and at all ages.

show abstract

“…Methods to forecast mortality based on compositional data have been previously developed, forecasting life table deaths (Bergeron-Boucher et al, 2017Kjaergaard et al, 2020;Oeppen, 2008). We suggest using the method of Oeppen (2008) to forecast state-and-age-specific life table deaths.…”

Section: Sullivan-based Forecast Model (Codas)mentioning

confidence: 99%

Modeling and forecasting healthy life expectancy with Compositional Data Analysis

Bergeron-Boucher¹,

Strozza²,

Simonacci³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Will the extra years of life gained by the increase in life expectancy be lived in good or poor health? As forecasts support social, economic and medical decisions, as well as individuals' choices, there is a clear rationale for forecasting healthy life expectancy (HLE). However, only a limited number of models is available to forecast HLE. We here suggest two models to forecast health and mortality simultaneously and coherently. One model is based on the Sullivan method to estimate HLE and the second one on the multistate life table method. Both models use Compositional Data Analysis (CoDA) to account for the coherence between health and mortality. Mortality and health at age 50 and above is forecast for Spanish and Swedish females. Both models provide similar estimates and forecasts of HLE, estimating and predicting a compression of morbidity in Sweden and a dynamic equilibrium in Spain.

show abstract

Longevity Forecasting by Socio-Economic Groups Using Compositional Data Analysis

Cited by 13 publications

References 42 publications

Insight into stagnating adult life expectancy: Analyzing cause of death patterns across socioeconomic groups

Insight into stagnating adult life expectancy: Analyzing cause of death patterns across socioeconomic groups

Mortality forecasting at age 65 and above: an age-specific evaluation of the Lee-Carter model

Modeling and forecasting healthy life expectancy with Compositional Data Analysis

Contact Info

Product

Resources

About