Counts of the U.S. Hispanic population are available every ten years from the decennial census, but for the years following or between censuses, estimates have to be created using data and techniques that are expected to track changes in that population over time. Such estimates are a recent development and there is currently no standard methodology that has been widely used, carefully documented, and rigorously tested. In this article, we describe an experimental methodology for estimating the Hispanic population of states and counties.
This article is a review of–and response to–a special issue of Mathematical Population Studies that focused on the relative performance of simpler vs. more complex population projection models.
Net migration has been widely criticized as a theoretical concept and as a measure of population movement. Many of these criticisms are valid: net migration reflects a residual rather than a true migration process, it often masks large gross migration flows, it cannot account for differences in the characteristics of origin and destination populations, it cannot be used for rates in a probabilistic sense, and it can lead to misspecified causal models and unrealistic population projections.
Estimates of the Hispanic population have traditionally been based on historical trends, ratios, or some variant of the cohort-component method. In this article, we describe and test a methodology in which estimates of the Hispanic population are based on symptomatic indicators of population change such as births, deaths, and school enrollments. Methods. Using a variety of techniques, we develop Hispanic population estimates for counties in Florida. We evaluate the accuracy of those estimates by comparing them with 2000 census counts.