Abstract
International migration flows are considered the most difficult demographic component to forecast and, for that reason, models for forecasting migration are few and relatively undeveloped. This is worrying because, in developed societies, international migration is often the largest component of population growth and most influential in debates about societal and economic change. In this paper, we address the need for better forecasting models of international migration by testing a hierarchical (bilinear) model within the Bayesian inferential framework, recently developed to forecast age and sex patterns of immigration and emigration in the United Kingdom, on other types of migration flow data: age- and sex-specific time series from Sweden, South Korea, and Australia. The performances of the forecasts are compared and assessed with the observed time-series data. The results demonstrate the generality and flexibility of the model and of Bayesian inference for forecasting migration, as well as for further research.
Notes
1 James Raymer is at the School of Demography, Australian National University. Arkadiusz Wiśniowski is in the Social Statistics Department, University of Manchester. Please direct all correspondence to James Raymer, School of Demography, Australian National University, 9 Fellows Road, Acton, ACT 2601, Australia; or by E-mail: [email protected]
2 The authors would like to thank Jakub Bijak, Peter Smith, and Jon Forster for their comments and advice on earlier drafts of this paper. The ESRC National Centre for Research Methods International Visitor Exchange Scheme supported Arkadiusz Wiśniowski in visiting the Australian National University to work on this paper.