Forecasting demographic forecasts

Juha M. Alho

International Journal of Forecasting, 2014, vol. 30, issue 4, 1128-1135

Abstract: Consider the financial sustainability of public finances in the context of stochastic demographics. Such analyses have typically been made under the assumption that future demographic developments are deterministic. When stochastic demographics have been considered, the problems have been simplified by assuming that the decision makers in the economic system behave as if they had perfect foresight as regards demographics. More realistically, we assume that the decision makers base their decisions on the forecasts of the future population, but revise their decisions when it turns out that the demographics do not follow the expected path. We contrast the nature of demographic uncertainty with that of financial markets, and argue that it is not realistic to assume that the revisions will occur according to the full rational expectations paradigm. Instead, the decision makers are assumed to revise according to the most recent point forecast. To implement this approach, we tailor standard nonparametric regression techniques to the task of computing the required future conditional expectations. Specifically, we assume that an approximation to the predictive distribution of the future population is available in terms of simulated population counts. The required conditional expectations are then obtained by averaging the future evolution of a set of sample paths that come from the neighborhood of a target path. This is formally equivalent to n-nearest neighbor kernel regression. The degree of smoothing can be chosen via cross-validation. An illustration based on a stochastic forecast of the population of Finland is given.

Keywords: Conditional expectation; Forecast update; Population forecast; Rational expectations; Uncertainty (search for similar items in EconPapers)
Date: 2014
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (8)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0169207014000478
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:intfor:v:30:y:2014:i:4:p:1128-1135

DOI: 10.1016/j.ijforecast.2014.02.005

Access Statistics for this article

International Journal of Forecasting is currently edited by R. J. Hyndman

More articles in International Journal of Forecasting from Elsevier
Bibliographic data for series maintained by Catherine Liu ().