Research Programme

Probabilistic population forecasting

Peter W.F. Smith, Jakub Bijak, Jon ForsterErengul DoddJason HiltonArek Wiśniowski

Project summary

The aim of this research is to continue developing the pathbreaking models and tools made during CPC-I on dynamic population forecasting models, particularly in the context of demographic uncertainty. Dynamic population models provide a general and flexible platform for modelling and analysing population change over time. They allow the combination of all the main components of population change by age and sex with various transitions that population groups may experience throughout their life course. The transitions may include those between states of residences, employment, marriage or health.

The models developed in this project extend existing multi-state models by (1) including all of the main demographic components of change (i.e., fertility, mortality and interregional migration) and their (expected) variations over time, (2) by allowing interactions to occur between various state transitions that occur throughout the life course, e.g., health and marital statuses, residential and employment statuses, or marital and employment statuses, and (3) by including uncertainty using statistical modelling approaches for rates and categorical data.


Project activities

Date Activity Description
12-14 September 2016 2016 BSPS Conference held at the University of Winchester Jason Hilton presents the paper "Integrated probabilistic population forecasts for the United Kingdom: A Bayesian approach" co-authored by Jakub Bijak, Erengul Dodd, Jon Forster and Peter Smith.
19-22 June 2016 Presentation at the 36th International Symposium on Forecasting held in Santander, Spain. Jason Hilton presents the paper "An Intergrated Framework For Bayesian Population Forecasting."
13-17 June 2016 Presentation at the International Society for Bayesian Analysis (ISBA) Conference 2016 held in Sardinia, Italy. Peter Smith presents the paper "An Integrated Framework For Bayesian Population Forecasting." Jakub Bijak is a discussant for the Bayesian Demography session.
16 May 2016 Presentation at the First International Conference on "EU andGlobal Asylum-Related Migration Research - Gaining an Overview" organised by the EASO and held in Floriana, Malta Presentation by Jakub Bijak on "Modelling Migration: Review and Assessment."
18-20 April 2016 Presentation at the Conference of European Statisticians: The paper 'A Comprehensive Framework for Mortality Forecasting' was presented by Jakub Bijak.
25-28 June 2014 'Incorporating model uncertainty into fertility schedule estimates for population forecasting’, European Population Conference, Budapest Presented by Jon Forster
19 June 2014 Workshop on the use of probabilistic forecasts, Royal Statistical Society, London CPC hosted event
30 May 2014 Dealing with uncertainty in migration research’, Turkish Migration Conference 2014, Regent's University London Presented by Jakub Bijak
28 May 2014 Invited seminar, Oxford Institute of Ageing, University of Oxford Presented by Jakub Bijak
29 April 2014  Joint World Bank/KNOMAD-United Nations Population Division seminar on the role of Migration in Population Modeling, New York Presented by Jakub Bijak
10 April 2014  Invited seminar, School of Mathematics, University College Dublin  Presented by Jakub Bijak
9 January 2014  Invited seminar, Centre for Demographic Studies, Autonomous University of Barcelona Presented by Jakub Bijak












Wiśniowski, A., Bijak, J. and Shang, H. L.  (2014)  Forecasting Scottish migration in the context of the 2014 constitutional change debate. Population Space and Place, 20, (5), 455-464.


Media activities

You can browse all CPC media outputs and population-related articles from CPC members on our! page.