@article{goes2026_115181,
  title = {Probabilistic population forecasts for small regions},
  author = {Goes, Julius and Engelhardt, Henriette},
  year = {2026},
  pages = {719-762},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-115181x},
  url = {https://fis.uni-bamberg.de/handle/uniba/115181},
  language = {eng},
  abstract = {Background: Age-specific population forecasts for small areas or subnational regions are a valuable tool for local governments. However, typical population projection methods based on the cohort-component approach are difficult to apply on a smaller subnational scale.

Objective: We introduce Bayesian methods suitable for obtaining reliable age-specific population forecasts for small regions using the cohort-component method.

Methods: Our approach improves fertility forecasting by extending the Lee–Carter model with an age-region interaction term. We propose to forecast net-migration counts using skewed error terms, and introduce a Dirichlet regression to model migration age patterns as well as age proportions of fertility.

Results: We run our model to produce age-specific population forecasts for a set of 13 heterogeneous regions in Bavaria, Germany. We compare our method with other standard approaches and find that it produces superior out-of-sample forecasts according to both point measures and scoring rules.

Conclusions: The findings suggest that the proposed Bayesian methods offer good predictive accuracy and are suitable in obtaining precise forecasts of age-specific population for smaller geographical regions.

Contribution: We introduce a new method for the probabilistic projection of subnational population that works well and outperforms other current methods.},
  keywords = {population}
}

@article{goes2026_114726,
  title = {Probabilistic population forecasts for small regions},
  author = {Goes, Julius and Engelhardt, Henriette},
  year = {2026},
  journal = {Demographic Research},
  volume = {54},
  number = {23},
  pages = {719-762},
  publisher = {Max Planck Institute for Demographic Research},
  address = {Rostock},
  issn = {2363-7064},
  doi = {10.4054/demres.2026.54.23},
  url = {https://fis.uni-bamberg.de/handle/uniba/114726},
  language = {eng},
  abstract = {Background: Age-specific population forecasts for small areas or subnational regions are a valuable tool for local governments. However, typical population projection methods based on the cohort-component approach are difficult to apply on a smaller subnational scale.

Objective: We introduce Bayesian methods suitable for obtaining reliable age-specific population forecasts for small regions using the cohort-component method.

Methods: Our approach improves fertility forecasting by extending the Lee–Carter model with an age-region interaction term. We propose to forecast net-migration counts using skewed error terms, and introduce a Dirichlet regression to model migration age patterns as well as age proportions of fertility.

Results: We run our model to produce age-specific population forecasts for a set of 13 heterogeneous regions in Bavaria, Germany. We compare our method with other standard approaches and find that it produces superior out-of-sample forecasts according to both point measures and scoring rules.

Conclusions: The findings suggest that the proposed Bayesian methods offer good predictive accuracy and are suitable in obtaining precise forecasts of age-specific population for smaller geo-graphical regions.

Contribution: We introduce a new method for the probabilistic projection of subnational population that works well and outperforms other current methods.},
  keywords = {population}
}

@article{goes2026_114418,
  title = {Bayesian mortality modelling with pandemics : a vanishing jump approach},
  author = {Goes, Julius and Barigou, Karim and Leucht, Anne},
  year = {2026},
  pages = {1-43},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-114418x},
  url = {https://fis.uni-bamberg.de/handle/uniba/114418},
  language = {eng},
  abstract = {This paper extends the Lee-Carter model for single- and multi-populations to account for pandemic jump effects of vanishing kind, allowing for a more comprehensive and accurate representation of mortality rates during a pandemic, characterised by a high impact at the beginning and gradually vanishing effects over subsequent periods. While the Lee-Carter model is effective in capturing mortality trends, it  may not always be able to account for large, unexpected jumps in mortality rates caused by pandemics or wars. Existing models allow either for transient jumps with an effect of one period only or persistent jumps. However, there is no literature on estimating mortality time series with jumps having an effect over a small number of periods, as is typically observed in pandemics. The Bayesian approach allows to quantify the uncertainty around the parameter estimates. Empirical data from the COVID-19 pandemic show the superiority of the proposed approach, compared to models with a transitory shock effect.},
  keywords = {Stochastic mortality modelling, Pandemic shocks, jump effects, Bayesian inference}
}

@phdthesis{goes2026_112551,
  title = {Advances in Bayesian Demographic Forecasting},
  author = {Goes, Julius},
  year = {2026},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  doi = {10.20378/irb-112551},
  urn = {urn:nbn:de:bvb:473-irb-112551x},
  url = {https://fis.uni-bamberg.de/handle/uniba/112551},
  language = {eng},
  abstract = {Demographic forecasting is essential for planning infrastructure, healthcare, and social services, yet traditional population projections—often deterministic and scenario-based—fail to capture uncertainty or provide probabilistic insights. This thesis advances probabilistic population forecasting by developing Bayesian methods for mortality, fertility, and net-migration, enabling accurate age-specific population predictions at national and regional scales.
The first chapter introduces spatial extensions to the Lee-Carter and Age-Period-Cohort models, improving regional mortality forecasts by accounting for spatial correlation and using Bayesian stacking for robustness. The second chapter addresses pandemic-induced mortality shocks, proposing a model for correlated jumps that better reflects the gradual decline of excess deaths observed during events like COVID-19. Finally, the thesis integrates these methods into a probabilistic cohort-component framework, applying it to subnational regions in Upper Franconia, Bavaria. By combining regionalized forecasts of mortality, fertility, and migration—including Dirichlet regression for migration patterns—this work enhances the precision and reliability of small-area population projections.},
  keywords = {Bevölkerungsprognose, Bayes Statistik, Demographie, Zeitreihenanalyse},
  school = {Otto-Friedrich-Universität Bamberg}
}

@article{goes2025_114295,
  title = {Bayesian mortality modelling with pandemics : a vanishing jump approach},
  author = {Goes, Julius and Barigou, Karim and Leucht, Anne},
  year = {2025},
  journal = {Journal of the Royal Statistical Society. Series C, Applied statistics},
  volume = {74},
  number = {4},
  pages = {1150–1182},
  publisher = {Oxford University Press},
  address = {Kettering ; Cary, NC ; Tokyo},
  issn = {1467-9876},
  doi = {10.1093/jrsssc/qlaf018},
  url = {https://fis.uni-bamberg.de/handle/uniba/114295},
  language = {eng},
  abstract = {This paper extends the Lee-Carter model for single- and multi-populations to account for pandemic jump effects of vanishing kind, allowing for a more comprehensive and accurate representation of mortality rates during a pandemic, characterised by a high impact at the beginning and gradually vanishing effects over subsequent periods. While the Lee-Carter model is effective in capturing mortality trends, it  may not always be able to account for large, unexpected jumps in mortality rates caused by pandemics or wars. Existing models allow either for transient jumps with an effect of one period only or persistent jumps. However, there is no literature on estimating mortality time series with jumps having an effect over a small number of periods, as is typically observed in pandemics. The Bayesian approach allows to quantify the uncertainty around the parameter estimates. Empirical data from the COVID-19 pandemic show the superiority of the proposed approach, compared to models with a transitory shock effect.},
  keywords = {Stochastic mortality modelling, Pandemic shocks, jump effects, Bayesian inference}
}

@article{goes2024_95818,
  title = {Bayesian Forecasting of Mortality Rates for Small Areas Using Spatiotemporal Models},
  author = {Goes, Julius Alexander},
  year = {2024},
  pages = {1-44},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-958189},
  url = {https://fis.uni-bamberg.de/handle/uniba/95818},
  language = {eng},
  abstract = {Estimation and prediction of subnational mortality rates for small areas are essential planning tools for studying health inequalities. Standard methods do not perform well when data are noisy, a typical behavior of subnational datasets. Thus, reliable estimates are difficult to obtain. I present a Bayesian hierarchical model framework for prediction of mortality rates at a small or subnational level. By combining ideas from demography and epidemiology, the classical mortality modeling framework is extended to include an additional spatial component capturing regional heterogeneity. Information is pooled across neighboring regions and smoothed over time and age. To make predictions more robust and address the issue of model selection, a Bayesian version of stacking is considered using leave-future-out validation. I apply this method to forecast mortality rates for 96 regions in Bavaria, Germany, disaggregated by age and sex. Uncertainty surrounding the forecasts is provided in terms of prediction intervals. Using posterior predictive checks, I show that the models capture the essential features and are suitable to forecast the data at hand. On held-out data, my predictions outperform those of standard models lacking a regional component.},
  keywords = {Mortality Forecasting, Subnational Estimation, Spatiotemporal Models, Stacking, Bayesian Hierarchical Models}
}

@article{goes2024_95053,
  title = {Bayesian Forecasting of Mortality Rates for Small Areas Using Spatiotemporal Models},
  author = {Goes, Julius},
  year = {2024},
  journal = {Demography},
  volume = {61},
  number = {2},
  pages = {439-462},
  publisher = {DUKE University Press},
  address = {Austin},
  issn = {1533-7790},
  doi = {10.1215/00703370-11212716},
  url = {https://fis.uni-bamberg.de/handle/uniba/95053},
  language = {eng},
  abstract = {Estimation and prediction of subnational mortality rates for small areas are essential planning tools for studying health inequalities. Standard methods do not perform well when data are noisy, a typical behavior of subnational datasets. Thus, reliable estimates are difficult to obtain. I present a Bayesian hierarchical model framework for prediction of mortality rates at a small or subnational level. By combining ideas from demography and epidemiology, the classical mortality modeling framework is extended to include an additional spatial component capturing regional heterogeneity. Information is pooled across neighboring regions and smoothed over time and age. To make predictions more robust and address the issue of model selection, a Bayesian version of stacking is considered using leave-future-out validation. I apply this method to forecast mortality rates for 96 regions in Bavaria, Germany, disaggregated by age and sex. Uncertainty surrounding the forecasts is provided in terms of prediction intervals. Using posterior predictive checks, I show that the models capture the essential features and are suitable to forecast the data at hand. On held-out data, my predictions outperform those of standard models lacking a regional component.},
  keywords = {Mortality Forecasting, Subnational Estimation, Spatiotemporal Models, Stacking, Bayesian Hierarchical Models}
}

@misc{goes2023_92071,
  title = {Bayesian mortality modelling with pandemics : a vanishing jump approach},
  author = {Goes, Julius Alexander and Barigou, Karim and Leucht, Anne},
  year = {2023},
  number = {Version: November 10, 2023},
  pages = {1-35},
  publisher = {arXiv},
  doi = {10.48550/arxiv.2311.04920},
  url = {https://fis.uni-bamberg.de/handle/uniba/92071},
  language = {eng}
}

