A note on the use of regression methods in population estimates.

Evidence which has emerged in the past few years indicates that the relative accuracy of population estimates derived from the ratio-correlation method and the difference-correlation method varies from state to state. In assessing the possible reasons why neither technique is uniformly more accurate, attention is focused on the temporal instability of the statistical relationships between symptomatic indicators and population change. The author concludes that further improvement in population estimates based on regression techniques is likely to be limited until demographers derive means of measuring and adjusting for these temporal changes.