Forecasting place-to-place migration with generalized linear models

Abstract

The consideration of place-to-place migration flows for regional population projection leads to two basic issues. In this chapter, the authors focus on the internal dynamics of the multiregional system, in particular on the identification of the inertia and stationarity in the linkages (migration). The data base consists of a time-series of place-to-place migration flows. The authors design generalized linear models (GLMs) for the time-series data on the components. Migration has always been thought of as the most volatile component of demographic dynamics. Since 1958 the Central Bureau of Statistics (CBS) of the Netherlands has classified municipalities by degree of urbanization. Initially the classification was based on the characteristics of the municipalities as revealed by the 1947 population census and the 1956 housing census. The total number of migrations in the Netherlands follows the pattern which is seen in most of the Western European countries. Migration is often the most important component of regional population change.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 24 citations exist upstream.