President Obama said in his inaugural address that he planned to "restore science to its rightful place" in government. That's a worthy goal. But statisticians at the Commerce Department didn't think it would mean having the director of next year's Census report directly to the White House rather than to the Commerce secretary, as is customary. "There's only one reason to have that high level of White House involvement," a career professional at the Census Bureau tells me. "And it's called politics, not science."
The decision was made last week after California Rep. Barbara Lee, chair of the Congressional Black Caucus, and Hispanic groups complained to the White House that Judd Gregg, the Republican senator from New Hampshire slated to head Commerce, couldn't be trusted to conduct a complete Census. The National Association of Latino Officials said it had "serious questions about his willingness to ensure that the 2010 Census produces the most accurate possible count."
Anything that threatens the integrity of the Census has profound implications. Not only is it the basis for congressional redistricting, it provides the raw data by which government spending is allocated on everything from roads to schools. The Bureau of Labor Statistics also uses the Census to prepare the economic data that so much of business relies upon. "If the original numbers aren't as hard as possible, the uses they're put to get fuzzier and fuzzier," says Bruce Chapman, who was director of the Census in the 1980s.
Mr. Chapman worries about a revival of the effort led by minority groups after the 2000 Census to adjust the totals for states and cities using statistical sampling and computer models. In 1999, the Supreme Court ruled 5-4 in Department of Commerce v. U.S. House that sampling could not be used to reapportion congressional seats. But it left open the possibility that sampling could be used to redraw political boundaries within the states.
Such a move would prove controversial. "Sampling potentially has the kind of margin of error an opinion poll has and the same subjectivity a voter-intent standard in a recount has," says Mr. Chapman.
Starting in 2000, the Census Bureau conducted three years of studies with the help of many outside statistical experts. According to then Census director Louis Kincannon, the Bureau concluded that "adjustment based on sampling didn't produce improved figures" and could damage Census credibility.
The reason? In theory, statisticians can identify general numbers of people missed in a head count. But it cannot then place those abstract "missing people" into specific neighborhoods, let alone blocks. And anyone could go door to door and find out such people don't exist. There can be other anomalies. "The adjusted numbers told us the head count had overcounted the number of Indians on reservations," Mr. Kincannon told me. "That made no sense."
The problem of counting minorities and the homeless has long been known. Census Bureau statisticians believe that a vigorous hard count, supplemented by adding in the names of actual people missed by head counters but still found in public records, is likely to lead to a far more defensible count than sampling-based adjustment.
The larger debate prompted seven former Census directors — serving every president from Nixon to George W. Bush — to sign a letter last year supporting a bill to turn the Census Bureau into an independent agency after the 2010 Census. "It is vitally important that the American public have confidence that the census results have been produced by an independent, non-partisan, apolitical, and scientific Census Bureau," it read.
The directors also noted that "each of us experienced times when we could have made much more timely and thorough responses to Congressional requests and oversight if we had dealt directly with Congress." The bill's chief sponsor is New York Democratic Rep. Carolyn Maloney, who represents Manhattan's Upper East Side.
"The real issue is who directs the Census, the pros or the pols," says Mr. Chapman. "You would think an administration that's thumping its chest about respecting science would show a little respect for scientists in the statistical field." He worries that a Census director reporting to a hyperpartisan such as White House Chief of Staff Rahm Emanuel increases the chances of a presidential order that would override the consensus of statisticians.
The Obama administration is downplaying how closely the White House will oversee the Census Bureau. But Press Secretary Robert Gibbs insists there is "historical precedent" for the Census director to be "working closely with the White House."
It would be nice to know what Sen. Gregg thinks about all this, but he's refusing comment. And that, says Mr. Chapman, the former Census director, is damaging his credibility. "He will look neutered with oversight of the most important function of his department over the next two years shipped over to the West Wing," he says. "If I were him, I wouldn't take the job unless I had that changed."
