Demographic estimates of the total resident population of states and counties have been a standard data product of the U.S. Census Bureau for many years. The traditional reference point for these population estimates is July 1 of the specified year. Until 1996, the county-level estimates were restricted to the total population, while the state estimates included separate estimates by age, sex, and race/Hispanic origin. The requirements of this project and of several other data users resulted in the expansion of the county estimates program to include age, sex, and race/Hispanic origin detail. This project requires estimates of the total resident population and the following age groups: under age 5, ages 5 to 17 years, under age 65, and age 65 and over.
Population estimates and administrative tax return data are used together as predictor variables in the models. The population estimates cover all residents, while the tax data cover people with filing requirements. The tax data omit two groups, the non-compliant and those without filing requirements. The non-compliant are not easily described by age or income class, but those without filing requirements are. People with low income and the elderly are less likely to have income that exceeds tax filing thresholds.
In the state-level models, the dependent variable, i.e., the variable predicted for each state, is the ratio of numbers of people in poverty to population as measured in the American Community Survey (ACS). To transform these ratios into estimated numbers of people in poverty, we multiply each estimated ratio by a demographic estimate of the population as covered by the ACS. Note the 2005 ACS universe did not include group quarters populations, such as residents of nursing homes, college dormitories, correctional institutions, and other group quarters populations. But the 2006 ACS universe and onward does include these groups.
Finally, we use estimates of the poverty universe at both the state and county levels to compute the percentages of people in poverty shown in the tables of SAIPE estimates. We form poverty universe estimates from the population estimates by adjusting them to exclude other population subgroups (e.g., foster children under age 15) and to limit the estimates of the number of children to related children. We describe these adjustments in more detail in the section on Denominators for State and County Poverty Rates.
For information on population estimates used before 2005, see Postcensal Estimates of the Population: 1993 - 2004.
More on the Population Estimates Program.