Bayesian functional models in population forecasting

Han Lin Shang; Arkadiusz Wisniowski; Jakub Bijak; Peter Smith; James Raymer

Bayesian functional models in population forecasting

Han Lin Shang^*, Arkadiusz Wisniowski, Jakub Bijak, Peter Smith, James Raymer

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

Abstract

We explore the functional modelling approach to population forecasting within the wider context of Bayesian predictions and model uncertainty. The functional modelling approach can be used to analyse and forecast different age- and time-specific components for fertility, mortality and migration. For each of these demographic processes, we perform Bayesian model averaging across the outcomes of two functional models to take into account model uncertainty. We illustrate the method with a population forecast for the United Kingdom for 2010-2030. We conclude that regularities in age profiles of demographic processes, where available, provide important information for the forecasts and as such should be included in the forecasting process.

Original language	English
Title of host publication	Proceedings of the Sixth Eurostat/Unece Work Session on Demographic Projections
Place of Publication	Roma
Publisher	Istituto nazionale di statistica
Pages	313-325
Number of pages	13
ISBN (Electronic)	9788845818103
ISBN (Print)	9788845818110
Publication status	Published - 2014
Externally published	Yes
Event	Sixth Eurostat/Unece Work Session on Demographic Projections - Rome, Italy Duration: 29 Oct 2013 → 31 Oct 2013

Conference

Conference	Sixth Eurostat/Unece Work Session on Demographic Projections
Country/Territory	Italy
City	Rome
Period	29/10/13 → 31/10/13

Keywords

Age schedules
Bayesian model selection
Functional models
LeeCarter model
Model uncertainty
Population forecasting

Cite this

@inproceedings{5f9a5fc615d44d9b9bac4a3a1190206e,

title = "Bayesian functional models in population forecasting",

abstract = "We explore the functional modelling approach to population forecasting within the wider context of Bayesian predictions and model uncertainty. The functional modelling approach can be used to analyse and forecast different age- and time-specific components for fertility, mortality and migration. For each of these demographic processes, we perform Bayesian model averaging across the outcomes of two functional models to take into account model uncertainty. We illustrate the method with a population forecast for the United Kingdom for 2010-2030. We conclude that regularities in age profiles of demographic processes, where available, provide important information for the forecasts and as such should be included in the forecasting process. ",

keywords = "Age schedules, Bayesian model selection, Functional models, LeeCarter model, Model uncertainty, Population forecasting",

author = "Shang, {Han Lin} and Arkadiusz Wisniowski and Jakub Bijak and Peter Smith and James Raymer",

year = "2014",

language = "English",

isbn = "9788845818110",

pages = "313--325",

booktitle = "Proceedings of the Sixth Eurostat/Unece Work Session on Demographic Projections",

publisher = "Istituto nazionale di statistica",

note = "Sixth Eurostat/Unece Work Session on Demographic Projections ; Conference date: 29-10-2013 Through 31-10-2013",

}

Bayesian functional models in population forecasting. / Shang, Han Lin; Wisniowski, Arkadiusz; Bijak, Jakub et al.

Proceedings of the Sixth Eurostat/Unece Work Session on Demographic Projections. Roma : Istituto nazionale di statistica, 2014. p. 313-325.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Bayesian functional models in population forecasting

AU - Shang, Han Lin

AU - Wisniowski, Arkadiusz

AU - Bijak, Jakub

AU - Smith, Peter

AU - Raymer, James

PY - 2014

Y1 - 2014

N2 - We explore the functional modelling approach to population forecasting within the wider context of Bayesian predictions and model uncertainty. The functional modelling approach can be used to analyse and forecast different age- and time-specific components for fertility, mortality and migration. For each of these demographic processes, we perform Bayesian model averaging across the outcomes of two functional models to take into account model uncertainty. We illustrate the method with a population forecast for the United Kingdom for 2010-2030. We conclude that regularities in age profiles of demographic processes, where available, provide important information for the forecasts and as such should be included in the forecasting process.

AB - We explore the functional modelling approach to population forecasting within the wider context of Bayesian predictions and model uncertainty. The functional modelling approach can be used to analyse and forecast different age- and time-specific components for fertility, mortality and migration. For each of these demographic processes, we perform Bayesian model averaging across the outcomes of two functional models to take into account model uncertainty. We illustrate the method with a population forecast for the United Kingdom for 2010-2030. We conclude that regularities in age profiles of demographic processes, where available, provide important information for the forecasts and as such should be included in the forecasting process.

KW - Age schedules

KW - Bayesian model selection

KW - Functional models

KW - LeeCarter model

KW - Model uncertainty

KW - Population forecasting

UR - https://www.istat.it/it/files//2014/11/Atti_Unece_Eurostat.pdf.pdf

M3 - Conference proceeding contribution

SN - 9788845818110

SP - 313

EP - 325

BT - Proceedings of the Sixth Eurostat/Unece Work Session on Demographic Projections

PB - Istituto nazionale di statistica

CY - Roma

T2 - Sixth Eurostat/Unece Work Session on Demographic Projections

Y2 - 29 October 2013 through 31 October 2013

ER -

Bayesian functional models in population forecasting

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this