Improving the measurement of temporal change in regression models used for county population estimates

Abstract

The ratio-correlation method of population estimation is shown to contain an inconsistent temporal relationship between the model’s empirical structure and its actual application. A simple transformation of the model’s variables is provided that eliminates the inconsistency. Two tests of the relative accuracy of the original and transformed models show that the transformed model achieves accuracy levels equal to or higher than the original. In one test, all nine years show a higher degree of accuracy, of which four are statistically significant. Several possible reasons are given for the increased accuracy shown by the transformed model. The transformation, termed the “rate-correlation” model, is recommended as a logical starting point in the examination of coefficient stability and spatial autocorrelation as well as a method for estimating small populations.