[Last update 2002apr22]Utah Census 2000
Utah, et al. v. Evans, Secy of Commerce 01-0714
Reprinted with permission from "On The Docket"
Appealed From: U.S. District Court for Utah (3-judge panel) (Nov. 5, 2001)
Subject: Census, "imputation," household estimation, apportionment
Question(s) presented: (1) Whether the use of "imputation," under which the number of residents in a housing unit whose occupancy could not otherwise be determined was based on the known number of residents of a similar nearby unit, violated 13 U.S.C. 195, which prohibits "the use of the statistical method known as 'sampling'" in determining the population "for purposes of apportionment of Representatives in Congress among the several States." (2) Whether the use of imputation violated the Census Clause of the Constitution, Art. I, � 2, Cl. 3.
Utah has a small population and only three members in the House of Representatives. But the 2000 Census presented the Beehive State with an opportunity to raise its political representation in the House by 25 percent.
The census determined that Utah�s population increased from about 2.13 million in 1990 to more than 2.23 million in 2000. A state�s representation in Congress is determined by population counts gathered through the census. A variety of calculations go into determining apportionment, but according to statistics from the U.S. Census bureau, after the 2000 census, each House Representative now represents an average population of 647,000.
Utah is arguing that its population increase by nearly 30 percent would yield another seat were it not for a statistical method called "imputation." Imputation is used when census-takers have been unsuccessful in gathering data from a particular household. After numerous failed attempts, they enter data based on a neighboring household of similar size. In 2000, imputation accounted for less than 0.5 percent of the population statistics gathered. But the method added around 32,000 people to North Carolina�s population, while it accounted for only about 5, 400 people in Utah.
North Carolina got an additional House seat, its 13th, which Utah had hoped to gain. In calculating the apportionment of representatives, most states clearly lost or added House seats. But the margin was very close between these two states. Were the 32,000 people in North Carolina that census-takers could not contact not counted as part of the population, Utah would have won the seat.
Utah figured that if it could challenge the constitutionality of imputation, it might win that seat back. In November of 2001 the state took its case to federal court in Utah.
Utah argued that the process violated section 13 U.S.C. 195 of the Census Act, which specifically "prohibits the proposed uses of statistical sampling in calculating the population, for purposes of apportionment."
The state also argued that imputation violated the constitutional requirement on "actual enumeration." The Constitution states: "Representatives shall be apportioned among the several States according to their respective numbers, counting the whole number of persons in each State." By conducting a census every 10 years and using "actual enumeration," the government hoped to monitor population shifts and maintain equal representation in the government.
The Justice Department disagreed with Utah, arguing that the case "lacked merit" and and that, within the meaning of the law, imputation did not constitute statistical sampling.
A divided three-judge federal panel in Utah dismissed the suit.
The majority concluded that "section 195 [of the Census Act] does not preclude the Census Bureau from the use of every type of statistical methodology in arriving at apportionment figures during a decennial census." It only prohibits "sampling," the process whereby a scientifically selected group of units is used to represent the entire population they come from. The court found imputation to be a different and more accurate process because it was used to determine the value of missing data for a single household.
Senior District Judge J. Thomas Greene dissented, arguing that "�sampling� and �imputation� in substance and effect are indistinguishable because both use a portion of the population to infer information concerning segments of the population in order to arrive at final figures concerning the population as a whole."
The majority also found that imputation was not a violation of the "actual enumeration" census clause of the Constitution. Instead, looking at the enormity of the task at hand in conducting a census every ten years, the court found it "inconceivable that the Constitution prohibits the use of statistical methodologies to account for missing and incomplete data."
Because it is inevitable that some people will not respond to census data requests and gaps will ensue, the court said, "some type of imputation must take place by practical necessity whether it is the imputation of statistically plausible values for the missing data or the imputation of a zero."
The process of imputing zero was what Utah wanted the court to enforce, thereby giving them the disputed representative, but the judges argued that such an approach would be "inconsistent with the constitutional imperative of actual enumeration," because ostensibly actual residents would not be counted.
On Jan. 22, 2002, the U.S. Supreme Court accepted the case for review, indicating it would consider the question of jurisdiction as it reviews the case on the merits.
The following day, Utah moved to expedite the case for consideration during the 2001-02 term, so that the Court's decision might apply to the November 2002 elections, in which Utah could add an additional Congressional seat, possibly at the expense of one in North Carolina.
The Court granted the motion and set oral arguments for March 27.
Attorneys in this case:
For Donald L. Evans, Secretary of Commerce (U.S.):
For North Carolina, et al.: