Accuracy of count data transferred through the areal weighting interpolation method

Abstract

This paper analyzes the accuracy of count data transferred from a zonal system to an incompatible zone through the areal weighting interpolation method. To treat a variety of situations in a theoretical framework, stochastic models representing areal weighting interpolation are developed. The relationship between the accuracy of estimates and the size of source zones is analytically investigated by use of a proposed model. The results strongly suggested that smaller zones give better estimates on a wide range of zonal systems. The effect of the shape of source zones and the target zone on estimation accuracy is also numerically examined, and it was found to be significant as well as the effect of the size of source zones.2

A Method for Exploring Long-Term Urban Change Using National Historical GIS Databases

“…This again produced challenges. Areal interpolation techniques, in which data are interpolated based on the area of intersection between two sets of administrative boundaries, work most accurately when used to interpolate from smaller units to more aggregated ones and when the boundaries of the two sets of units are similar (Sadahiro 2000). In our case, the 1971 parishes are more aggregated than the wards in urban areas but less aggregated in rural areas, and this makes area-based interpolation difficult.…”

Error‐sensitive historical GIS: Identifying areal interpolation errors in time‐series data

“…Sadahiro (2000) shows that error will be reduced where source zones are relatively small compared with the target zones, and that the relative shapes of the source and target zones will also affect accuracy. Sadahiro (1999) shows that the utility of ancillary information will vary according to its relevance to y and that adding inappropriate ancillary information may actually reduce the accuracy of interpolation compared with simple areal weighting.…”

Geographic Information Systems and Spatial Data Processing in Demography: a Review

“…This approach was notably used by Allen and Turner (2002). It has the distinct advantage of a more fine-grained surface of source zones from which to assemble the target territories, a property that tends to minimize error (Sadahiro 2000). Inasmuch as block aggregation uses observed counts it is very accurate.…”