Insights into the Decision on Whether to Statistically Adjust the 2000 Census for Coverage Errors

Abstract

AbstractThe decennial census is one of the cornerstones of our democracy. The Constitution requires that the Decennial Census be used for reapportioning the Congress of the United States. The decennial census has a myriad of other key uses including: redrawing Congressional and local voting districts; allocating over $900 billion of federal funds annually; informing sound policy development; providing critical information for state, local, and tribal government planning; and supplying critical information to large and small businesses to generate growth and job creation. Understandably, there are great concerns regarding the accuracy of the census by a wide array of stakeholders. No decennial census has been perfect, and historically, non-White and Hispanic population groups have been undercounted in the decennial census at a significantly higher rate than the White population. Early planning for the 2000 Census included the incorporation of statistical sampling and coverage measurement into the core processes. This became a hotly debated issue and resulted in litigation that ultimately went to the Supreme Court. This chapter will provide some background on the 2000 Census and will discuss the process the Census Bureau used to make recommendations on whether statistical adjustment of the Census 2000 results to correct for undercounts should be carried out.