Skip to content
DraconiticResearch
Search Sources API
186,625 studies31 sourcesUpdated 2 min ago
PreprintCC BY-NC-SA 4.0arXiv

Forecast reconciliation meets compositional data analysis: A study of Italian cause-specific age-at-death

  • Andrea Nigri
  • Giacomo Lanfiuti Baldi
  • Raffaele Mattera
  • Han Lin Shang
Open at sourcePDFDOICite

Abstract

We introduce a novel approach that integrates compositional data analysis (CoDA) in the forecasting of hierarchical and grouped time series and apply it to improve mortality forecasts. By leveraging the inherent decomposition of mortality data by cause of death and sex, our framework addresses key challenges in mortality forecasting, ensuring internal coherence across different levels of aggregation while maintaining high predictive accuracy. Our empirical results on Italian cause-specific mortality data demonstrate that the proposed approach significantly improves the reliability of forecasts compared to the traditional CoDA, especially for total mortality forecasts. Consistent improvements in forecasting accuracy are also found for total deaths by cause and by sex.

Related

  1. The Stairs of Reconciliation: A Mathematical Tourist in Graz
    Santiago Schnell
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  2. Bayesian Reconciliation of Overlapping Multi-Step Forecasts: A Post-Processing Framework for Cross-Origin Coherence
    Oluwatosin Bamidele Fajana, Ricardo S. Ehlers, Marinho G. Andrade
    arXivPreprintCC BY-NC-ND 4.0Full textStatisticsarXiv
  3. New classes of trace-form permutation polynomials and their compositional inverses
    Kirpa Garg
    arXivPreprintarXiv licenceFull textAlgebra & number theoryarXiv
  4. Compositional Synthetic Controls
    Onil Boussim
    arXivPreprintCC BY 4.0Full textStatisticsarXiv
  5. Target alignment, dilution and forecast selection when cross-sectional forecasts share a common target
    Masoud Soleimani
    arXivPreprintCC BY-NC-ND 4.0Full textStatisticsarXiv

Cite

BibTeXRIS
BibTeX
@misc{nigri2026forecast,
  title = {{Forecast reconciliation meets compositional data analysis: A study of Italian cause-specific age-at-death}},
  author = {Andrea Nigri and Giacomo Lanfiuti Baldi and Raffaele Mattera and Han Lin Shang},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.18987},
  eprint = {2609.18987},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.18987},
  note = {CC BY-NC-SA 4.0},
}
RIS
TY  - UNPB
TI  - Forecast reconciliation meets compositional data analysis: A study of Italian cause-specific age-at-death
AU  - Andrea Nigri
AU  - Giacomo Lanfiuti Baldi
AU  - Raffaele Mattera
AU  - Han Lin Shang
PY  - 2026
DA  - 2026/09/01
PB  - arXiv
DO  - 10.48550/arxiv.2609.18987
UR  - https://arxiv.org/abs/2609.18987
AB  - We introduce a novel approach that integrates compositional data analysis (CoDA) in the forecasting of hierarchical and grouped time series and apply it to improve mortality forecasts. By leveraging the inherent decomposition of mortality data by cause of death and sex, our framework addresses key challenges in mortality forecasting, ensuring internal coherence across different levels of aggregation while maintaining high predictive accuracy. Our empirical results on Italian cause-specific mortality data demonstrate that the proposed approach significantly improves the reliability of forecasts compared to the traditional CoDA, especially for total mortality forecasts. Consistent improvements in forecasting accuracy are also found for total deaths by cause and by sex.
ER  -