WASHINGTON, June 20 (UPI) -- The Supreme Court Thursday approved a U.S. census method of inferring how many people live in a particular area, which some have attacked as illegal "sampling."
The ruling means North Carolina gets to keep its new seat in Congress, which Utah said it deserved.
The ruling is also expected to give a slight boost to Democrats who are trying to take back control of the House in 2004. A Democrat is expected to have a better chance of winning in North Carolina than in Utah.
This was the second challenge to the 2000 Census mounted by Utah in an attempt to increase its population count and representation in Congress.
Last year, the state filed suit unsuccessfully to force the Census Bureau to count its overseas Mormon missionaries as part of Utah's population, pointing out that federal employees deployed abroad were nevertheless counted in their home states. The federal courts rejected that argument.
In the current challenge to "hot-deck imputation," the census counting method challenged by Utah, the Bush administration supported the Census Bureau practice.
The Census Bureau processed data for 120 million households in 2000. That included more than 147 million paper questionnaires and 1.5 billion pages of printed material.
"The Census Bureau's intensive efforts to obtain information directly from an individual at each address (or, if necessary, an individual familiar with that address) were not always successful," the Justice Department told the Supreme Court in a brief supporting the bureau and its parent, the Commerce Department. "When the bureau was otherwise unable to obtain information regarding the number of persons who resided in a particular housing unit on the census data, it employed 'imputation,' a widely-accepted procedure used to account for missing, discrepant or improperly processed data."
The "hot-deck imputation" method has been used by the Census Bureau since 1960. "Hot-deck" means that data used for comparison was taken from the same census; "cold-deck imputation" means the data came from an earlier census or some outside source.
"In the form of hot-deck imputation used in the 2000 census, housing unit and other data were stored sequentially in a computer file as they were processed," the department said. "When data for a particular unit were incomplete, data from the most recently processed housing unit with similar characteristics were imputed to it."
Utah filed suit in April 2000 saying that the imputation process violated the federal Census Act, which bars sampling, and the census clause of the Constitution, which calls for an "actual enumeration" of each state's population.
The state relied on the Supreme Court's 1999 ruling in Commerce Department vs. U.S. House, in which the justices said statistical sampling was banned by the federal Census Act, but not decide whether sampling violated the Constitution.
In the imputation challenge, a federal trial judge panel ruled 2-1 against Utah. The panel majority said the banned practice of sampling consisted of "the technique of determining the traits of the entire population by collecting and analyzing data" from a randomly drawn sample of the population.
In other words, the Census Bureau would "sample" a small segment of the population and extrapolate it to the whole population. Before 2000, the bureau wanted to use the technique to more accurately count minority segments of the population who are traditionally undercounted, but the practice was stopped by the 1999 Supreme Court ruling.
In contrast, the court panel majority said in the Utah suit, "hot-deck imputation" is a different methodology. "Sampling" occurs during the collecting of data; "hot-deck imputation" occurs during the processing of data.
After the panel's ruling, Utah appealed directly to the Supreme Court.
The justices heard argument last March.
Writing for the court majority, Justice Stephen Breyer upheld the court panel's ruling.
From the bench, he compared use of the "imputation" method to a librarian counting books on shelves.
The librarian notices gaps and assumes that the books are loaned out, Breyer said. Taking the average size of a book, the librarian divides that by how much shelf space is empty.
That's roughly analogous to what the Census Bureau did with imputation, the justice said.
Given the fact that the Census Bureau "made every effort to reach every household, where the methods used consist not of statistical sampling but of inference, where that inference involves a tiny percent of the population, where the alternative is to make a far less accurate assessment of the population and where consequently manipulation of the method is highly unlikely," the court could not say that "imputation" exceeded the limits of the census clause of the Constitution, Breyer said.
Three justices dissented in part. Justice Sandra Day O'Connor said imputation violated the Census Act. Justice Clarence Thomas, joined by Justice Anthony Kennedy, said imputation violated the "actual enumeration" required by the census clause.
Justice Antonin Scalia wrote a separate dissent in which he said Utah did not have "standing" to bring the suit in the first place.
(No. 01-714, Utah et al vs. Sec. Evans et al)
