Projecting UK Mortality by Using Bayesian Generalized Additive Models

Hilton, Jason; Dodd, Erengul; Forster, Jonathan J.; Smith, Peter

doi:10.1111/rssc.12299

Cited by 23 publications

(26 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Formulated as a generalized additive model, the model of Hilton et al . () is advantageous in being less challenging to estimate and incorporate parameter smoothing. Although Hilton et al .…”

Section: Resultsmentioning

confidence: 99%

“…Although Hilton et al . () developed the estimation procedure in a Bayesian setting, they did not consider the possibility of having missing data. To utilize their model for our application, an external imputation model for imputing missing death counts would seem necessary.…”

Section: Resultsmentioning

confidence: 99%

“…The recent model of Hilton et al (2019) merits some discussion. Ignoring its cohort term, this model is quite similar to the Lee-Carter model that we consider in terms of structure and number of parameters.…”

Section: Resultsmentioning

confidence: 99%

“…Ignoring its cohort term, this model is quite similar to the Lee-Carter model that we consider in terms of structure and number of parameters. Formulated as a generalized additive model, the model of Hilton et al (2019) is advantageous in being less challenging to estimate and incorporate parameter smoothing. Although Hilton et al (2019) developed the estimation procedure in a Bayesian setting, they did not consider the possibility of having missing data.…”

Section: Resultsmentioning

confidence: 99%

“…Formulated as a generalized additive model, the model of Hilton et al (2019) is advantageous in being less challenging to estimate and incorporate parameter smoothing. Although Hilton et al (2019) developed the estimation procedure in a Bayesian setting, they did not consider the possibility of having missing data. To utilize their model for our application, an external imputation model for imputing missing death counts would seem necessary.…”

Section: Resultsmentioning

confidence: 99%

See 4 more Smart Citations

A Bayesian Approach to Developing a Stochastic Mortality Model for China

Li¹,

Zhou

Zhu

et al. 2019

Journal of the Royal Statistical Society Series A: Statistics in Society

View full text Add to dashboard Cite

Summary Stochastic mortality models have a wide range of applications. They are particularly important for analysing Chinese mortality, which is subject to rapid and uncertain changes. However, owing to data‐related problems, stochastic modelling of Chinese mortality has not been given adequate attention. We attempt to use a Bayesian approach to model the evolution of Chinese mortality over time, taking into account all of the problems associated with the data set. We build on the Gaussian state space formulation of the Lee–Carter model, introducing new features to handle the missing data points, to acknowledge the fact that the data are obtained from different sources and to mitigate the erratic behaviour of the parameter estimates that arises from the data limitations. The approach proposed yields stochastic mortality forecasts that are in line with both the trend and the variation of the historical observations. We further use simulated pseudodata sets with resembling limitations to validate the approach. The validation result confirms our approach's success in dealing with the limitations of the Chinese mortality data.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 3 more Smart Citations

A Bayesian Approach to Developing a Stochastic Mortality Model for China

Li¹,

Zhou

Zhu

et al. 2019

Journal of the Royal Statistical Society Series A: Statistics in Society

View full text Add to dashboard Cite

show abstract

Unifying mortality forecasting model: an investigation of the COM–Poisson distribution in the GAS model for improved projections

Rakhmawan,

Mahmood,

Abbas

et al. 2024

Lifetime Data Anal

View full text Add to dashboard Cite

Forecasting mortality rates is crucial for evaluating life insurance company solvency, especially amid disruptions caused by phenomena like COVID-19. The Lee–Carter model is commonly employed in mortality modelling; however, extensions that can encompass count data with diverse distributions, such as the Generalized Autoregressive Score (GAS) model utilizing the COM–Poisson distribution, exhibit potential for enhancing time-to-event forecasting accuracy. Using mortality data from 29 countries, this research evaluates various distributions and determines that the COM–Poisson model surpasses the Poisson, binomial, and negative binomial distributions in forecasting mortality rates. The one-step forecasting capability of the GAS model offers distinct advantages, while the COM–Poisson distribution demonstrates enhanced flexibility and versatility by accommodating various distributions, including Poisson and negative binomial. Ultimately, the study determines that the COM–Poisson GAS model is an effective instrument for examining time series data on mortality rates, particularly when facing time-varying parameters and non-conventional data distributions.

show abstract

The slowdown in mortality improvement rates 2011–2017: a multi-country analysis

et al. 2022

View full text Add to dashboard Cite

Mortality rates have been falling or ‘improving’ in many demographically developed countries since the 1950s. However, there has been a slowdown since 2010 in the speed of improvement and this phenomenon has been particularly marked at ages over 50. To understand better this mortality slowdown, we have analysed long-run mortality trends of a group of developed countries using data up to 2017 from the Human Mortality Database. Specifically, we have used statistical models to parametrise the historical mortality trends of 21 countries between 1965 and 2010 and then forecast trends beyond 2011. We find that many countries have experienced lower mortality improvement rates in 2011–2017 than in the previous decade and also experienced lower improvement rates in 2011–2017 than would have been forecast based on the models fitted to data prior to 2011. Some of the Scandinavian populations have bucked the stalling mortality improvement trend, experiencing higher mortality improvement rates than the forecasts. We conclude that part of the slowdown in mortality improvement rates of the over 1950s since 2011 would have been expected from historical trends in many countries, especially among men. However, there has been a notable slowdown since 2011, compared with the model forecasts, in many countries especially among women. A few countries had higher mortality improvement rates than forecast. A better understanding of the drivers behind these complex trends would help decision makers in insurance companies and pension funds and also inform public policy.

show abstract

Projecting UK Mortality by Using Bayesian Generalized Additive Models

Cited by 23 publications

References 30 publications

A Bayesian Approach to Developing a Stochastic Mortality Model for China

A Bayesian Approach to Developing a Stochastic Mortality Model for China

Unifying mortality forecasting model: an investigation of the COM–Poisson distribution in the GAS model for improved projections

The slowdown in mortality improvement rates 2011–2017: a multi-country analysis

Contact Info

Product

Resources

About