Small Area Estimation of School District Child Population and Poverty: Studying Use of IRS Income Tax Data

Disclaimer: This paper is released to inform interested parties of research and to encourage discussion. The views expressed are those of the authors and not necessarily those of the U.S. Census Bureau. Summary The Small Area Income and Poverty Estimates (SAIPE) program provides estimates for selected income and poverty statistics for states, counties, and school districts. The main objective of this program is to provide updated estimates of income and poverty statistics for the administration of federal programs and the allocation of federal funds to local jurisdictions. In particular, the No Child Left Behind Act of 2001 directs the Department of Education to distribute Title I basic and concentration grants directly to school districts on the basis of the most recent Census Bureau estimates of school-age children in poverty in each school district in the U.S. While direct poverty estimates for school districts were produced from the 1990 and 2000 censuses, producing updated (post-censal) estimates at the school district level presents some challenging problems. Until recently there were no available data sources tabulated for school districts that provided reliable, updated information related to poverty. Therefore, the current official SAIPE method for producing updated school district child poverty estimates relies on a synthetic approach. The previous census results are used to estimate the proportions (shares) of the numbers of poor school-age children in each county who were in each school district that was wholly or partially contained in that county. (We refer to the intersections of counties and school districts as " school district pieces. ") These shares are then carried forward through the decade and, to produce school district piece poverty estimates for a given year, they are multiplied by the SAIPE model-based county estimates of the numbers of poor school-age children in that year. The poverty estimates for the pieces are then appropriately summed to produce the poverty estimates for the school districts. This process also requires retabulating the previous census results each year to account for school district boundary changes. Apart from dealing with the boundary changes, this approach provides updated information on poverty only down to the county level – there is no updated information on the distribution of poverty within counties since the school district piece to county poverty shares remain constant. Recent tabulations of IRS income tax data for school districts provide potentially useful sources of updated information on the distribution of poverty across school …