Towards Bayesian Model-Based Demography

Jakub Bijak is Professor of Statistical Demography at the University of Southampton. He has background in economics (PhD 2008, Warsaw School of Economics) and over 20 years’ work experience in academia and international civil service. His research focuses on demographic uncertainty, population and migration models and forecasts, and the demography of armed conflict. He has been awarded the Allianz European Demographer Award (2015) and the Jerzy Z Holzer Medal (2007) for work on migration modelling. Leader of a European Research Council project “Bayesian agent-based population studies” (www.baps-project.eu), and a Horizon 2020 project “QuantMig: Quantifying Migration Scenarios for Better Policy” (www.quantmig.eu).

“The material collected by Jakub Bijak and his team constitutes a valuable resource for scholars interested in modelling individual decisions, not necessarily restricted to migration processes. … Researchers who already gained some experience in social simulation will receive many inspirations for improving their own research and rise to the next level. In this way, this book has the potential to advance the art of modelling in the social sciences.” (Thomas Fent, European Journal of Population, Vol. 38, 2022)

• Part I: Preliminaries: Chapter 1. Introduction.- Chapter 2. Uncertainty and complexity: towards model-based demography.- Part II: Elements of the modelling process.- Chapter 3. Principles and state of the art of agent-based migration modelling.- Chapter 4. Building a knowledge base for the model.- Chapter 5. Uncertainty quantification, model calibration and sensitivity.- Chapter 6. The boundaries of cognition and decision making.- Chapter 7. Agent-based modelling and simulation with domain-specific languages.- Part III: Model results, applications, and reflections.- Chapter 8. Towards more realistic models.- Chapter 9. Bayesian model-based approach: impact on science and policy.- Chapter 10. Open science, replicability, and transparency in modelling.- Chapter 11. Conclusions: towards a Bayesian modelling process.