Community Research and Development Information Service - CORDIS

Abstract

Forecasts of the age/sex composition of the population in 18 countries of the European Economic Area (EEA) omitting Liechtenstein, but including Switzerland have been compiled up to 2050. The principal innovative aspect is that forecast uncertainty is quantified: predictive intervals are computed, that specify the probability that the future population will be between x and y million, and likewise for all age groups, at each year in the future. The statistical dependency across countries is taken into account. The traditional approach (applied by the UN, Eurostat and most national agencies) is merely to run deterministic variant projections, for example assuming high fertility, life expectancy and net migration levels, without attaching probability content to them. The project has demonstrated that for the countries considered:
1. Long-term stochastic population forecasts by sex and age may significantly differ from latest population scenarios of Eurostat and the UN, and from national population forecasts both in terms of how the most likely future demographic development is assessed, and how forecast uncertainty is taken into account.
2. The parameter values of the predictive distributions of future fertility, mortality and migration can be successfully derived from a methodology that combines the findings of three different methods: analysis of observed errors in past forecasts, model-based estimates of forecast errors, and elicitation of expert opinions.
3. In spite of the lack of internationally consistent data series on international migration, the production of multi-national stochastic population forecasts is feasible.
4. Ageing is certain, and a modest population growth for the group of countries as a whole to the horizon 2050 is likely. However, the speed of population ageing is quite uncertain.

Additional information

Authors: ALDERS M, Statistics Netherlands, Voorburg (NL);KEILMAN N, Central Bureau of Statistics, Oslo (NO);ALHO J, University of Joensuu, Joensuu (FI);NIKANDER T, Tilastokeskus, Helsinki (FI)
Bibliographic Reference: EUR 21699 EN (2005), 146pp. Free of charge
Availability: Katalogue Number: KI-NA-21699-EN-S The paper version can be ordered online at: http://bookshop.europa.eu
ISBN: ISBN: 92-894-9832-3
Record Number: 200618566 / Last updated on: 2006-04-28
Category: PUBLICATION
Original language: en
Available languages: en