Bayesian Forecasting of Immigration to Selected European Countries by using Expert Knowledge

Abstract

The aim of the paper is to present Bayesian forecasts of immigration for seven European countries to 2025, based on quantitative data and qualitative knowledge elicited from country-specific migration experts in a two-round Delphi survey. In line with earlier results, most of the immigration processes under study were found to be barely predictable in the long run, exhibiting non-stationary features. This outcome was obtained largely irrespectively of the expert knowledge input, which nevertheless was found useful in describing the predictive uncertainty, especially in the short term. It is argued that, under the non-stationarity of migration processes, too long forecasts horizons are inadequate, which is a serious challenge for population forecasts in general. Copyright (c) 2010 Royal Statistical Society.

Integrated Modeling of European Migration

“…The Delphi survey followed the example of a similar, migration-related endeavor (Bijak and Wiśniowski 2010), and consisted of a two-round process, with anonymized first-round feedback to the experts provided before the second round. In principle, this provides an opportunity for the experts to converge on views.…”

“…Most of this work has been focused on indirect methods for particular countries (e.g., Warren and Peck 1980;Jasso and Rosenzweig 1982;Hill 1985;Zaba 1987; Van der Gaag and Van Wissen 2002;Bijak 2010;Bijak and Wiśniowski 2010). There are, however, several recent papers on harmonizing and estimating migration flow tables from which we can draw experiences.…”

Integrating uncertainty in time series population forecasts: An illustration using a simple projection model

“…2013) provide good starting points. However, as the projection models become more complex, the relative importance of expert opinion will increase (see Bijak and Wiśniowski (2010) ). Fortunately, the Bayesian approach allows data and uncertainty in parameters and model choice to be fully quantified using probability distributions.…”

“…In this paper, model uncertainty is directly integrated with parameter uncertainty into a single predictive probability distribution. A comprehensive review of Bayesian model averaging is available in Hoeting et al (1999), and for some demographic applications, see Bijak (2010) and Bijak and Wiśniowski (2010).…”

Utilising Expert Opinion to Improve the Measurement of International Migration in Europe

“…The resulting estimates are then based on posterior distributions, which combine these expert beliefs with other available information, including all relevant data sources and covariates. The posterior distributions can also be used to quantify uncertainty in the estimates, providing the users, such as governments and planning agencies, with valuable additional information to design their policies directed at supplying particular social services or at influencing levels of migration (Bijak and Wiśniowski 2010).…”