Small-area population forecasting in an urban setting: A spatial regression approach

This study revisits a spatial regression approach for small-area population forecasting that considers not only direct drivers of local area population growth but also neighbour growth and neighbour characteristics. Previous research suggested that the approach does not outperform extrapolation projections, the currently most-often-used small-area population forecasting technique. We argue the reason is that population growth is affected by its influential factors differently in urban, suburban, and rural areas. Therefore, we hypothesize that the spatial regression forecasting approach can perform better in one type of area at a time, where the influential factors' effects on population growth can be estimated more accurately. This study is focused on census tracts of the city of Milwaukee, USA, to test the performance of the spatial regression approach in an urban setting. The analyses reveal mixed results and do not suggest that the spatial regression approach unambiguously outperforms extrapolation projections.