Small-Area Population Forecasting Using a Spatial Regression Approach

Guangqing Chi, University of Wisconsin at Madison
Paul R. Voss, University of Wisconsin at Madison

Existing demographic techniques do not work well for small-area population forecasts, because they generally ignore the effects of non-demographic (such as geophysical and socioeconomic) factors on population change. In this study we examine the ability of a spatial econometric forecasting approach for small-area population forecasting. In particular, a spatial lag model is applied to examine population change at the Minor Civil Division (MCD) level in Wisconsin since 1970. For each MCD, the population growth rate for 1980-1990 is regressed on its growth rate for 1970-1980, its various characteristics in 1980, and neighborhood characteristics in 1980 and growth rates for 1970-1980. The estimated coefficients (β’s) and spatial parameter (λ) are then used for projecting population in 2000. The accuracy is assessed by the Mean Algebraic Percent Error and Mean Absolute Percent Error. The capability of the spatial regression approach for small-area population forecasting can be seen.