NY Times: Census nominee shuns sampling as counting method

From the NY Times:

Robert M. Groves, President Obama’s nominee to lead the Census Bureau, told senators at a confirmation hearing on Friday that he would not seek to use statistical sampling in the 2010 census, offering reassurance to Republicans who have long opposed any effort to adjust for inevitable counting errors using mathematical models.

Mr. Groves, in testimony before the Senate Homeland Security and Government Oversight Committee, said that he supported the view of the Secretary of Commerce, Gary Locke, who oversees the Census Bureau, and who said there were no plans to use statistical sampling in the 2010 count.

“I agree fully with Secretary Locke’s testimony that statistical adjustment of the census is eliminated as an option for reapportionment and further that statistical adjustment will not be used for redistricting,” Mr. Groves said in his prepared opening statement. “The 2003 decision of Director Kincannon, consistent with this, assured that no implementation infrastructure for adjustment was put in place for 2010.”

Mr. Groves, 60, is a sociology professor and survey expert at the University of Michigan. He served as associate director of the Census Bureau in the 1990s, when President Clinton battled fiercely with Republican lawmakers in an effort to adopt statistical sampling as a way to correct for counting errors. House Republicans sued Mr. Clinton and won a court victory barring the use of sampling for the reapportionment of Congressional seats or for redistricting.


Many experts believe that sampling would be more accurate than using only an actual count, because millions of people are missed or refuse to be counted. Studies have found those missed are far more likely to be poor and ethnic and racial minority Americans in urban areas. Counting them would likely favor Democrats.

Many Republicans remain concerned that the Obama administration will try to adopt sampling as part of the census count.