Skip Header

Mark E. Asiala
Component ID: #ti1634784425

Prior to 2006, the American Community Survey (ACS) had produced inconsistent estimates of households and householders and inconsistent estimates of husbands and wives in married couple households even though logically these estimates should be equal. With the Family Equalization Project, research was undertaken to remedy these differences using a three-dimensional raking methodology where, for two of the dimensions, the marginal control totals are derived from the survey itself rather than an independent source. The results from that research led to changes in the weighting methodology for the 2006 ACS. This paper evaluates the effects of that change in both the 2006 and 2007 ACS single-year estimates. The focus of this paper is to assess the effects at the weighting area level where the raking was performed. We also looked at the effects on estimates for cities and towns.

Back to Header