View PDF Version
In the Supreme Court of the United States
STATE OF UTAH, ET AL., APPELLANTS
DONALD L. EVANS, SECRETARY OF COMMERCE, ET AL.
ON APPEAL FROM THE UNITED STATES DISTRICT COURT
FOR THE DISTRICT OF UTAH
BRIEF FOR THE FEDERAL APPELLEES
THEODORE B. OLSON
Counsel of Record
ROBERT D. MCCALLUM, JR.
Assistant Attorney General
EDWIN S. KNEEDLER
Deputy Solicitor General
MALCOLM L. STEWART
Assistant to the Solicitor
MARK B. STERN
MICHAEL S. RAAB
JONATHAN H. LEVY
Department of Justice
Washington, D.C. 20530-0001
In the 2000 census, the Census Bureau used a process known as "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. The questions presented are as follows:
1. Whether appellants' challenge to the Census Bureau's use of imputation is justiciable.
2. Whether the use of imputation 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."
3. Whether the use of imputation violated the Census Clause of the Constitution, Article I, Section 2, Clause 3.
In the Supreme Court of the United States
STATE OF UTAH, ET AL., APPELLANTS
DONALD L. EVANS, SECRETARY OF COMMERCE, ET AL.
ON APPEAL FROM THE UNITED STATES
DISTRICT COURT FOR THE DISTRICT OF UTAH
BRIEF FOR THE FEDERAL APPELLEES
The opinion of the three-judge district court (J.S. App. 1a-34a) is not yet reported.
The judgment of the district court was entered on November 5, 2001. The notice of appeal (J.S. App. 35a-36a) was filed on November 5, 2001. The jurisdictional statement was filed on November 20, 2001. The jurisdiction of this Court is invoked under 28 U.S.C. 1253 and under Section 209(e)(1) of the Departments of Commerce, Justice, and State, the Judiciary, and Related Agencies Appropriations Act, 1998, Pub. L. No. 105-119, 111 Stat. 2482. On January 22, 2002, this Court issued an order postponing further consideration of the question of jurisdiction to the hearing of the case on the merits. J.A. 451; see pp. 13-16, infra.
1. The Constitution requires a decennial census for the purpose of determining the number of Representatives to which each State is entitled. Article I, Section 2, Clause 3 provides, in its first sentence, that "Representatives * * * shall be apportioned among the several States * * * according to their respective Numbers" (the Apportionment Clause). The second sentence then provides: "The actual Enumeration shall be made within three Years after the first Meeting of the Congress of the United States, and within every subsequent Term of ten Years, in such Manner as they shall by Law direct" (the Census Clause). Ibid. See also U.S. Const. Amend. XIV, § 2 ("Representatives shall be apportioned among the several States according to their respective numbers, counting the whole number of persons in each State, excluding Indians not taxed.").
2. The Census Act provides that the Secretary of Commerce "shall, in the year 1980 and every 10 years thereafter, take a decennial census of population as of the first day of April of such year." 13 U.S.C. 141(a). The "tabulation of total population by States" is to be completed and reported by the Secretary to the President within nine months after the April 1 census date. 13 U.S.C. 141(b). Within one week after the beginning of the first Session of Congress following the census, the President must transmit to Congress a statement showing the "whole number of persons in each State * * * and the number of Representatives to which each State would be entitled" under the statutorily prescribed "equal proportions" formula for apportioning Representatives. 2 U.S.C. 2a(a); see United States Dep't of Commerce v. Montana, 503 U.S. 442, 451-455 (1992). Under the apportionment law, "[e]ach State shall be entitled * * * to the number of Representatives shown in the statement" submitted by the President. 2 U.S.C. 2a(b). Within 15 days after receiving that statement, the Clerk of the House must "send to the executive of each State a certificate of the number of Representatives to which such State is entitled." Ibid.
The Census Act generally authorizes the Secretary to conduct the decennial census "in such form and content as he may determine." 13 U.S.C. 141(a). The Census Bureau and its Director assist the Secretary in performing his duties under the Census Act. See 13 U.S.C. 2, 21. The Act further states that "[e]xcept for the determination of population for purposes of apportionment of Representatives in Congress among the several States, the Secretary shall, if he considers it feasible, authorize the use of the statistical method known as 'sampling' in carrying out the provisions of this title." 13 U.S.C. 195. Section 195 was enacted in 1957, at the request of the Secretary of Commerce, and was amended to its present form in 1976. See Department of Commerce v. United States House of Representatives, 525 U.S. 316, 336, 338-339 (1999).
3. Since 1790, the basic method of census operations has been to attempt to contact every household in order to determine the aggregate number of persons residing within each dwelling unit. From 1810 through 1960, enumerators were required by statute to visit each home in person to make the requisite inquiries. See House of Representatives, 525 U.S. at 335. In 1964, Congress amended the Census Act to eliminate that requirement. See Act of Aug. 31, 1964, Pub. L. No. 88-530, 78 Stat. 737. In every subsequent census the Bureau has employed written questionnaires, mailed to every known residential address, as the primary method of enumeration. See J.A. 268 (Declaration of Howard Hogan, Director, Decennial Statistical Studies Div'n, Census Bureau (Hogan Decl.)). "[W]hen a member of the household could not be found, census-takers have historically relied on information from neighbors, landlords, postal workers, or other proxies. * * * This procedure was first formally authorized for the 1880 census." J.A. 253-254 (Hogan Decl.); see Act of Mar. 3, 1879, ch. 195, § 8, 20 Stat. 475.
The Census Bureau's intensive initial efforts to secure a complete and accurate count through the means described above are not entirely successful. When the available information regarding the number of persons who resided in a particular housing unit on the census date is incomplete or contradictory, the Bureau has employed "imputation" to account for missing, discrepant, or improperly processed data. See J.A. 250-252, 254, 256-257 (Hogan Decl.). "Imputation is recognized in the statistical community as a procedure that can improve the accuracy and reliability of censuses and surveys, and has been amply discussed and documented in the professional literature." J.A. 263 (Hogan Decl.) (citing sources). The Bureau has traditionally based the imputation on the characteristics of a nearby housing unit. See J.A. 256-257 (Hogan Decl.). The Bureau has concluded that imputing characteristics to a housing unit in such circumstances, rather than automatically attributing zero residents to the unit, improves the accuracy of the census because "studies have shown that a significant proportion of returns with questionable or incomplete data or unresolved status are actually valid, occupied housing units." J.A. 252 (Hogan Decl.).
Imputation may be used either because the Bureau is unable to contact a particular housing unit's occupants or others having some knowledge of the unit, or because the data obtained through direct contacts is contradictory or otherwise unusable. See, e.g., J.A. 99 ("incomplete data may result from such factors as partial enumeration, respondent refusal or other nonresponse, clerical handling (e.g., coding) of questionnaires and electronic processing of the questionnaires"). In the 1960 census, for example, imputation was used to address "mechanical difficulties * * * with * * * the computer imaging device used to record the questionnaires." J.A. 267 (Hogan Decl.). Thus, in some instances, "refusing to impute ignores some people that attempted to participate in the census." J.A. 263 (Hogan Decl.).
In the 1940 and 1950 censuses, the Bureau used imputation to account for missing data concerning the age or other demographic characteristics of household members, but not to determine the basic population counts used in apportioning Representatives among the States. J.S. App. 8a; J.A. 266-267 (Hogan Decl.). In every census starting in 1960, however, the Census Bureau has employed "count imputation"-i.e., imputation used in the determination of official population figures. See J.S. App. 8a; J.A. 266-270, 273, 275-276 (Hogan Decl.); A.R. C00376-C00380, C00394-C00395, C00418-C00425, C00431, C01388-C01389. The count-imputation method used by the Census Bureau since the 1960 census has been the "hot-deck" method, "in which the imputed information comes from the same census." J.A. 256 (Hogan Decl.).1 After each census, the Bureau has published procedural histories, analyses, and reports that describe the use of imputation. See, e.g., A.R. C00361, C00379, C00395-C00396, C00418, C00425.
Following the 1980 census, the State of Indiana sued the Secretary of Commerce because, as a result of count imputation, a Representative in the House shifted from Indiana to Florida. See Orr v. Baldrige, No. IP-81-604-C (S.D. Ind. July 1, 1985) (J.A. 110-119). In that suit, the parties ultimately stipulated, and the court agreed, that imputation was not sampling prohibited by 13 U.S.C. 195. See J.A. 113-114; J.S. App. 19a. The court in Orr explained (J.A. 114):
Sampling is the selection of a subset of units from a larger population in such a way that each unit of the population has a known chance of selection. Sampling is used where a scientifically selected set of units can be used to represent the entire population from which they are drawn. Inferences about the entire population can be based on sample results. Imputation, on the other hand, is a procedure for determining a plausible value for missing data. Imputation is used in both sample surveys and censuses with the goal of achieving as complete as possible an enumeration of the sampled or population units.
4. "In the 2000 census, the Census Bureau processed data for over 120 million households, including over 147 million paper questionnaires and 1.5 billion pages of printed material." J.S. App. 25a. The Bureau's efforts "to obtain a completed census questionnaire from every housing unit for the 2000 census" began with the development of a Decennial Master Address File (DMAF), "which contained the mailing address, street address, and census block location of every housing unit in the United States." Id. at 6a. "Addresses in the DMAF originated from official sources such as the 1990 census, the U.S. Postal Service, local governments, tribal governments, and Census Bureau enumerators. These addresses were validated and updated according to specific Bureau procedures." J.A. 256 (Hogan Decl.). The Bureau sought responses from residents of each address through a number of techniques designed to maximize the response rate, including mailed, hand-delivered, and enumerator-prepared questionnaires, complemented by community outreach. J.S. App. 7a; A.R. C00198-C00201, C00206-C00207. The Census Bureau then undertook extensive efforts to contact nonresponding households. Enumerators performed rechecks and telephone interviews, making up to six attempts to obtain interviews. If the Census Bureau was unable to establish direct contact with a resident of a particular housing unit, the Bureau sought the information from proxy respondents such as "a neighbor, rental agent, building manager, or other knowledgeable individual." J.A. 285 (Hogan Decl.); see A.R. C00819-C00841.
The Census Bureau employed count imputation when it was unable to obtain complete and consistent data on a particular dwelling unit from a household member or proxy respondent. J.S. App. 7a-8a. "Household size" imputation was used "when Bureau records indicated that the housing unit was occupied, but [the Bureau] had insufficient information as to the number of individuals residing in the unit." J.A. 444. "Occupancy" imputation was used "[w]hen Census Bureau records indicated that a housing unit existed but did not provide sufficient information to definitively classify it as either occupied or vacant." Ibid. "Status" imputation was used "[w]hen the Census Bureau's records had insufficient information about whether an address represented a valid, non-duplicated housing unit." Ibid. When data for a particular unit were missing or incomplete, data from a nearby unit in the same tract with similar characteristics were imputed to it. J.S. App. 8a; J.A. 255, 256-257, 266-267 (Hogan Decl.).
5. The Census Bureau initially adopted a plan for the 2000 census that included statistical sampling programs. See House of Representatives, 525 U.S. at 324-325. As in the 1960 through 1990 censuses, the Bureau's plan for the 2000 census also included count imputation to address data processing problems, as well as a variety of other statistical methodologies. J.A. 275-276, 280 (Hogan Decl.). The House of Representatives and various private parties filed suit to challenge two of the proposed sampling programs, arguing that the use of sampling in determining the population figures for the apportionment of Representatives among the States would violate 13 U.S.C. 195, as well as the Census Clause of the Constitution. In House of Representatives, the Court held that Section 195 "prohibits the proposed uses of statistical sampling in calculating the population for purposes of apportionment." 525 U.S. at 343. In light of its disposition of the plaintiffs' statutory claim, the Court found it unnecessary to resolve the constitutional question. Id. at 343-344.
6. Because the Census Bureau has never considered count imputation to be a form of "sampling" within the meaning of Section 195, its intention to use imputation in the 2000 census was unaffected by the Court's decision in House of Representatives. J.A. 279 (Hogan Decl.). Before the commencement of the 2000 census, the Bureau presented all details of its plan for the census, including its intention to use imputation, to the congressional committees charged with overseeing the census, the General Accounting Office, the Census Monitoring Board, the Inspector General of the Department of Commerce, and numerous advisory committees. J.A. 280-281 (Hogan Decl.); see, e.g., A.R. C01519, C01731, C01752, C01805, C01818-C01819. The Bureau conducted the census in accordance with the plans presented to Congress. A total of approximately 0.4% of the apportionment count (1.2 million persons) was attributable to imputation. J.S. App. 7a. That percentage was roughly in line with the 1970 and 1980 censuses, when approximately 900,000 and 761,400 persons, respectively, were attributable to imputation. J.A. 268-269, 270, 277-278 (Hogan Decl.).
7. If the Bureau had attributed zero residents to each of the housing units for which imputation was used, Utah would have been apportioned one additional and North Carolina one fewer Representative. J.S. App. 9a. The State of Utah and several elected Utah officials (appellants in this Court) brought suit, seeking to invalidate the use of imputation and to have one Representative reapportioned from North Carolina to Utah. Appellants alleged that the Bureau's use of imputation violated the Administrative Procedure Act (APA), 5 U.S.C. 701 et seq.; the Census Act; and the Census Clause of the Constitution. J.S. App. 9a. The State of North Carolina and several of its elected officials intervened as defendants. Id. at 2a. A three-judge district court convened under 28 U.S.C. 2284 granted the defendants' motion for summary judgment. J.S. App. 1a-34a.
a. Relying on this Court's decision in Franklin v. Massachusetts, 505 U.S. 788 (1992), the district court first held that appellants' Census Act and constitutional claims were justiciable. J.S. App. 9a-12a. Based on Franklin and on Utah v. Evans, 143 F. Supp. 2d 1290 (D. Utah) (Evans I), aff'd, 122 S. Ct. 612 (2001), however, the court held that appellants' APA claim was not justiciable. J.S. App. 12a-15a.2
b. On the merits, the district court held that 13 U.S.C. 195 does not prohibit the use of imputation in determining population figures for purposes of apportioning Representatives among the States. J.S. App. 16a-24a. The court observed that "section 195 does not preclude the Census Bureau from the use of every type of statistical methodology in arriving at apportionment figures during a decennial census. Instead, it prohibits only 'the use of the statistical method known as "sampling."'" Id. at 18a. The district court "conclude[d] that statistical sampling and imputation are separate statistical methodologies and that they were viewed as such at the time of the enactment of § 195." Ibid.
c. The district court further held that the Bureau's use of imputation in determining the population totals employed in apportioning Representatives did not violate the Census Clause of the Constitution. J.S. App. 24a-27a. The court observed that the text of the Census Clause, which provides that the decennial census shall take place "in such Manner as [Congress] shall by law direct," U.S. Const. Art. I, § 2, Cl. 3, "vests Congress with virtually unlimited discretion in conducting the decennial actual Enumeration." J.S. App. 24a (citing Wisconsin v. City of New York, 517 U.S. 1, 19 (1996)). Given "the enormity and complexity of" the decennial census, the court found it "inconceivable that the Constitution prohibits the use of statistical methodologies to account for missing and incomplete data." Id. at 25a. Because gaps in the recorded data are inevitable, the court explained, "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." Ibid.
The district court rejected appellants' contention that the phrase "actual Enumeration" in the Census Clause precludes count imputation or requires the use of a particular census methodology. The court concluded that "[t]he constitutional requirement of an enumerative census was simply to distinguish that process from the conjectural apportionment of the first Congress" set forth in Article I, Section 2, Clause 3 of the Constitution itself. J.S. App. 26a. The court also noted that "the phrase 'actual enumeration' * * * was added by the Committee of Style and Arrangement, a committee which did not operate to alter the substance of any of the resolutions passed by the Constitutional Convention." Ibid.
d. Senior District Judge Greene dissented. J.S. App. 28a-34a. Judge Greene would have held that the Bureau's use of imputation violated Section 195's prohibition on the use of "sampling" in the determination of population figures used to apportion Representatives among the States. Id. at 28a.
SUMMARY OF ARGUMENT
I. Appellants' challenge to the Census Bureau's use of count imputation is justiciable under this Court's decisions in United States Dep't of Commerce v. Montana, 503 U.S. 442 (1992), and Franklin v. Massachusetts, 505 U.S. 788 (1992). Those suits were filed after the President had transmitted to Congress his statement setting forth the number of Representatives to which each State was entitled. Despite the federal government's contentions that judicial review was unavailable, based in part on the perceived impropriety of a judicial order mandating reapportionment after the President had transmitted his report, this Court held both suits to be justiciable.
II. The Census Bureau's use of imputation does not violate 13 U.S.C. 195.
A. Among statisticians, the term "sampling" has a well-accepted meaning and refers to a strategy for collecting data. An essential feature of a "sampling" process is the deliberate selection, during the design phase of the survey, of a subset of the population that is believed to be representative of the whole. Imputation, by contrast, is a method of processing data that have already been collected.
B. The history and purposes of Section 195 confirm that the term "sampling" refers to a method of data collection and does not encompass imputation. For purposes other than apportionment, Congress first authorized and later directed the use of "sampling" (when the Secretary considers it feasible), in order to reduce the cost and burden on respondents that the census might otherwise entail. Congress was thus motivated by the perceived advantages of sampling as a data-collection method. With respect to the apportionment of Representatives, however, Congress believed that the Bureau should employ the most comprehensive feasible data-collection efforts.
Appellants do not contend that the Census Bureau should have made greater efforts to collect information from the housing units at issue here. Rather, their claim is that the Bureau should have attributed zero residents to each of the relevant dwelling units rather than imputing data from comparable nearby units. Absent any challenge to the Bureau's data-collection measures, appellants' suit does not implicate the concerns underlying Section 195.
C. The Census Bureau has used count imputation in every census since 1960 and has never expressed any doubt as to its legality. The Bureau's use of count imputation has repeatedly been brought to the attention of Congress and the public, particularly in connection with the 1980 census, when the State of Florida received a Representative that would have been apportioned to the State of Indiana if imputation had not been used. The Bureau's longstanding view that hot-deck imputation is not a form of "sampling" within the meaning of Section 195 is entitled to judicial deference.
D. The Census Bureau's use of "occupancy" and "status" imputation do not violate Section 195. Appellants' basic textual theory provides no basis for distinguishing "occupancy" and "status" imputation from "household size" imputation. Although the policy arguments favoring "household size" imputation are particularly strong, the Bureau has reasonably concluded that "occupancy" and "status" imputation will also increase the accuracy of the census.
III. The Census Bureau's use of count imputation is consistent with the Census Clause of the Constitution.
A. The text of the Census Clause does not prescribe a particular method of determining the population. Rather, the Census Clause provides that the census shall be conducted "in such Manner as [Congress] shall by Law direct." U.S. Const. Art. I, § 2, Cl. 3.
B. The drafting history of the Census Clause confirms that the Framers did not intend to restrict Congress's choice of census methodologies. The phrase "actual Enumeration" first appeared in the draft Constitution submitted to the Convention by the Committee of Style and Arrangement, which evidently regarded that phrase as substantively equivalent to the prior draft's directive that the "number" of each State's inhabitants "shall * * * be taken in such manner as [Congress] shall direct." The words "actual Enumeration" simply refer to the concrete undertaking of ascertaining the population of the States. The word "actual" also serves to distinguish the permanent basis for apportioning Representatives from the temporary allocation, based on speculation about the States' populations, that the Census Clause itself provided would be in effect until the first census took place.
C. The federal officials charged with conducting the decennial census have never attempted to contact each of the Nation's residents directly. Rather, since 1790, the Census Bureau and its predecessors have employed a household-by-household approach, seeking through various means to determine the aggregate number of occupants of every dwelling unit. The use of imputation does not differ in kind from the federal government's prior reliance on other evidence of household size that, while imperfect, is deemed sufficiently reliable to improve the accuracy of the count.
D. The requirement that a new "Enumeration" be conducted within every ten-year period was intended to ensure that the apportionment of Representatives would continue to correspond to the "respective Numbers" of the "several States." The decennial census can fulfill that purpose, however, only to the extent that it accurately determines the relative population shares of the individual States. To construe the phrase "actual Enumeration" to preclude techniques that are consistent with the traditional household-by-household approach and that would enhance the accuracy of the census would place the Census Clause at cross-purposes with the related constitutional provisions that the Clause was intended to implement.
I. UNDER THIS COURT'S PRECEDENTS, APPELLANTS' SUIT IS JUSTICIABLE
Pursuant to the procedure established by the apportionment law (see p. 2, supra), the President transmitted to Congress in January 2001 the statement showing the number of Representatives to which each State, including North Carolina, is entitled under the statutory apportionment formula. See 2 U.S.C. 2a. Under the apportionment law, each State is now entitled to the number of Representatives shown in the President's statement, "until the taking effect of a reapportionment under [2 U.S.C. 2a] or subsequent statute." 2 U.S.C. 2a(b). In their motion to affirm or dismiss, the North Carolina appellees contend (at 11-14) that this Court lacks authority to issue an order affecting the apportionment of Representatives that was set forth in the President's statement. Although that argument has considerable force as an original matter-indeed, the federal government advanced similar contentions in two prior cases -it appears to be foreclosed by this Court's precedents.
A. In United States Department of Commerce v. Montana, 503 U.S. 442 (1992), the Court considered and rejected the State of Montana's constitutional challenge to the statutorily prescribed "equal proportions" formula (2 U.S.C. 2a(a)) for apportioning Representatives among the States. The federal government argued in that case that Congress's choice among competing apportionment formulas "present[ed] a 'political question' not amenable to judicial resolution." 503 U.S. at 456. In support of that proposition, the government noted, inter alia, that under 2 U.S.C. 2a, "the President must send a formal statement to the House by the end of the census year containing the number of Representatives to which each State is entitled, and the Clerk must promptly certify the entitlement to the States." Gov't Br. at 31, Montana, supra (No. 91-860). The government argued that "[j]udical review in this context would seriously disrupt, confuse and delay apportionment within the States. There accordingly is 'an unusual need for unquestioning adherence to a political decision already made.'" Ibid. (quoting Baker v. Carr, 369 U.S. 186, 217 (1962)). In addition, the government pointed out that a judicial order allocating an additional Representative to the State of Montana would effectively require that a Representative be taken away from the State of Washington. The government stated that "because Washington is not a party to the case, the federal district court in Montana could not realistically enforce an order purporting to mandate the transfer of a Representative from Washington to Montana." Id. at 32; see also id. at 32-33 n.27.
Notwithstanding the federal government's arguments, this Court unanimously held that Montana's challenge to the "equal proportions" formula was justiciable. See 503 U.S. at 456-459. In reaching that conclusion, the Court presumably determined that it was capable of ordering effective relief if it found the statutory apportionment formula to be unconstitutional.
B. In Franklin v. Massachusetts, 505 U.S. 788 (1992), this Court considered and rejected a constitutional challenge to the manner in which the Census Bureau had allocated overseas federal personnel for purposes of determining the state-level population figures used to apportion Representatives. The government argued that the Secretary's decision was not judicially reviewable because the matter was "committed to agency discretion by law," 5 U.S.C. 701(a)(2), and because the relevant census "statutes preclude judicial review," 5 U.S.C. 701(a)(1). See Gov't Br. at 18-33, Franklin, supra (No. 91-1502). In support of that position, the government contended that it was "fundamentally incompatible" with the deadlines established by 2 U.S.C. 2a(a) "for a court * * * to review and set aside the apportionment made by the President's statement after the Clerk has informed the States of their entitlements." Gov't Br. at 33.
In an opinion concurring in part and concurring in the judgment, Justice Scalia expressed the view that the plaintiffs lacked standing to raise their constitutional claim. Justice Scalia would have held that the plaintiffs' injury was not redressable because the President could not be directed to issue a new certification regarding the number of Representatives to which each State was entitled. See 505 U.S. at 823-829. The other Members of the Court, however, disagreed. Four Justices found the redressability requirement to be satisfied on the ground that "it is substantially likely that the President and other executive and congressional officials would abide by an authoritative interpretation of the census statute and constitutional provision by the District Court, even though they would not be directly bound by such a determination." Id. at 803 (opinion of O'Connor, J.). Four other Justices concluded that the President's role in the statutory scheme was purely ministerial, and that the report of census figures by the Secretary of Commerce was therefore "final agency action" subject to judicial review under the APA. Id. at 808-816 (Stevens, J., concurring in part and concurring in the judgment). Those opinions appear to assume that (a) a judicial ruling in favor of the plaintiffs could be expected to trigger a new Executive Branch statement regarding the population of each State, and (b) that statement would be given operative legal effect, notwithstanding the fact that the President had already transmitted his report stating the number of Representatives to which each State was entitled. Cf. id. at 824 n.1 (opinion of Scalia, J.).
II. THE CENSUS BUREAU'S USE OF IMPUTATION IN DETERMINING THE POPULATION FOR PURPOSES OF APPORTIONING REPRESENTATIVES AMONG THE STATES IS PERMITTED BY THE CENSUS ACT
A. "Sampling" As Used In 13 U.S.C. 195 Is A Statistical Term Of Art That Refers To A Method Of Data Collection And Does Not Encompass Imputation
1. For purposes of determining the apportionment of Representatives among the States, 13 U.S.C. 195 prohibits "the use of the statistical method known as 'sampling.'" The statutory language clearly expresses Congress's intent to distinguish "sampling" from other "statistical method[s]" and to prohibit only the former. See J.S. App. 18a. In addition, Section 195's reference to "the statistical method known as 'sampling'" (emphasis added) reflects Congress's understanding, at the time of the provision's enactment in 1957, that the word "sampling" was a term of art with an established meaning.
Among statisticians, the term "sampling" has a well-accepted meaning and refers to a strategy for collecting data. See J.A. 257-259 (Hogan Decl.); J.A. 291-292 (Declaration of Joseph Waksberg (Waksberg Decl.)). Imputation, by contrast, is a method of processing data that have already been collected. Ibid. Thus, "sampling and imputation are two completely different procedures, based upon totally distinct principles and serving equally distinct purposes." J.A. 259 (Hogan Decl.) (internal quotation marks omitted).
As a standard textbook published shortly before the 1957 enactment of 13 U.S.C. 195 explained, "[a] sampling method is a method of selecting a fraction of the population in a way that the selected sample represents the population." P. Sukhatme, Sampling Theory of Surveys with Applications 1 (1954); see J.A. 260-261 (Hogan Decl.).3 That is, moreover, the common dictionary meaning of "sampling." See Webster's Third New International Dictionary 2008 (1993) (def. 1.b) ("assessment of the quality or character of a whole by examination of a sample"); ibid. ("sample"; def. 2.a) ("a representative portion of a whole: a small segment or quantity taken as evidence of the quality or character of the entire group or lot"). By contrast, imputation in the 2000 census was part of an effort to contact and take account of every individual housing unit, and was used only when missing, incomplete, or contradictory data created obstacles to the accomplishment of a complete census. The imputation used at that stage "was a completely deterministic procedure which utilized data from a predetermined neighbor. There was no process of selecting from among a set of similar units, and, as a result, no sampling." J.A. 290 (Waksberg Decl.).
2. In the district court, appellants submitted the declarations of Drs. Lara J. Wolfson and Donald B. Rubin in support of their claim that hot-deck imputation is a form of statistical sampling. Dr. Wolfson's declaration defined sampling as "the process of selecting a number of subjects [units] from all the subjects [units] in a particular group or universe." J.A. 75 (internal quotation marks omitted). As Dr. Hogan explained, that definition is potentially over-inclusive because it "does not make clear that, in sampling, the process of selecting a sample is a deliberate and purposeful activity occurring during the design phase of a survey." J.A. 260. Dr. Hogan further explained (ibid.):
Without this understanding, Dr. Wolfson's definition is broad enough to cover situations that have nothing to do with sampling. And with this understanding, Dr. Wolfson's definition does not encompass imputation. * * * [I]mputation is not a mechanism for selecting units during the design phase of a census or sample survey, but rather is a means of dealing with missing data in the data processing stage.
Dr. Rubin's declaration similarly defined sampling as "the process of obtaining data from a subset of a population (the subset is usually called the 'sample') from which estimates are made about characteristics of the entire population." J.A. 59. That definition "suffers from the same flaws as Dr. Wolfson's in that Dr. Rubin's definition does not incorporate the process of deliberately selecting a subset of the population during the design phase of a survey." J.A. 260 (Hogan Decl.).
In this Court, appellants appear to have abandoned reliance on the Wolfson and Rubin declarations. Their opening brief does not cite either declaration; nor do appellants identify any other authority stating in terms that imputation is a form of "sampling." Appellants rely instead on fragmentary quotations from a handful of scholarly texts that, in appellants' view, define the process of "sampling" in a way that encompasses imputation. See Br. 18-21. Those sources do not support appellants' position, however, because-consistent with the general understanding in the statistical community-they recognize that a process of deliberate selection of a representative subset during the design phase is an integral feature of a "sample." See, e.g., Br. 18 ("sample" is identified "usually by deliberate selection with the object of investigating the properties of the parent population or set") (quoting M. Kendall & W. Buckland, A Dictionary of Statistical Terms 254 (1957)); Br. 21 ("'sampling' is understood as 'the selection of part of an aggregate of material to represent the whole'") (quoting F. Yates, Sampling Methods for Censuses and Surveys 1 (2d ed. 1953)).
B. The History And Purposes Of 13 U.S.C. 195 Confirm That The Term "Sampling" Refers To A Method Of Data Collection And Does Not Encompass Imputation
The Census Bureau's use of imputation is fully consistent with the congressional judgments that underlie Section 195's ban on the use of sampling for purposes of apportionment.
1. The types of sampling at which Section 195 was originally directed, such as the "long form" used for "gathering supplemental, nonapportionment census information regarding population, unemployment, housing, and other matters collected in conjunction with the decennial census," House of Representatives, 525 U.S. at 337, involve efforts to collect data only from persons within a selected sample. Congress authorized the use of such sampling procedures for purposes other than apportionment not because they were deemed likely to produce more accurate results than could be obtained through direct inquiries of all members of the population. Rather, the enactment of Section 195 in 1957, and its amendment in 1976, reflected Congress's view that use of sampling techniques can often produce acceptably accurate figures while reducing the cost to the government and burden on respondents that the census might otherwise entail. See, e.g., S. Rep. No. 698, 85th Cong., 1st Sess. 3 (1957) ("The proper use of sampling methods can result in substantial economies in census taking."); S. Rep. No. 1256, 94th Cong., 2d Sess. 5 (1976) (stating, with respect to the mid-decade census, that "the use of sampling procedures and surveys is urged for the sake of economy and reducing respondent burden"); see also id. at 9, 12, 13.4 In first authorizing and then directing the Secretary to use "the statistical method known as 'sampling'" (when he considers it feasible) for purposes other than apportionment, Congress was thus motivated by the perceived advantages of sampling as a data-collection method.
By the same token, Congress's decision that sampling should not be used to determine apportionment figures appears to rest on the view that, with respect to so fundamental an undertaking as the apportionment of Representatives among the States, the Bureau should employ the most comprehensive feasible data-collection efforts. In House of Representatives, the Court held that the Section 195 prohibits the use of sampling for apportionment purposes not only as a substitute for, but also as a supplement to, traditional enumeration methods. 525 U.S. at 342. But even when sampling is used to supplement initial good-faith efforts to contact all residents directly, it involves a conscious decision by the Census Bureau to undertake additional data-collection efforts with respect to some housing units while deliberately declining to employ the same efforts for other, comparable units. Under the Census Bureau's initial plan for the 2000 census, for example, the Bureau would have conducted nonresponse followup on only a randomly selected sample of the housing units that did not respond to the mailed questionnaires, until at least 90% of the units in each tract were accounted for. Id. at 324. As a result of the Court's decision in House of Representatives, however, the Bureau undertook followup efforts with respect to all nonresponding units. A.R. C00278.5
In the instant case, the housing units for which population data were imputed were not selected for less intensive data-collection efforts than the units from which the imputed data were drawn. Nor do appellants contend that the Bureau could or should have made additional efforts to contact persons within the units at issue. In fact, their challenge to the Bureau's use of imputation has nothing to do with the manner in which data were collected. Instead, their claim is that, when the Census Bureau was unable to obtain complete and consistent population data regarding a particular housing unit from the unit's occupants or from proxy respondents, the Bureau should have simply attributed zero residents to the unit in question rather than imputing data from a comparable nearby unit-even where the indications were that the unit was occupied and an attribution of zero therefore would have been knowingly inaccurate. Contrary to appellants' contention, however, Congress's decision to prohibit the use of "sampling" in the determination of apportionment figures does not speak to the appropriate choice between those two alternative means of dealing with the inevitable occurrence of missing or contradictory data at the data-processing phase of the census.6
2. Precisely because "the process of selecting a sample is a deliberate and purposeful activity occurring during the design phase of a survey," J.A. 260 (Hogan Decl.), it has been suggested that the use of sampling in determining the population for purposes of apportioning Representatives among the States might give rise to the fact or appearance of political manipulation. Cf. House of Representatives, 525 U.S. at 348-349 (Scalia, J., concurring in part). In hot-deck imputation, by contrast, neither the number nor the identity of the "donor" or "donee" units is pre-selected by the Bureau. Indeed, if the Bureau's other efforts to collect missing data and resolve inconsistencies were wholly successful, imputation would not be used at all. Because the imputation of figures to a particular unit is simply an ex post response to a gap in the collected data, Congress could reasonably conclude that it is unlikely to be used in a manipulative fashion.
Appellants contend (Br. 27-28) that if the hot-deck method is permitted, the Bureau could expand its use of imputation by reducing the resources devoted to nonresponse followup. But whether or not the Bureau uses imputation at the data-processing stage, it has very substantial latitude to determine what followup data-collection efforts should be employed for housing units that fail to respond to the initial questionnaire. If the Census Bureau automatically attributed zero occupants to each unit for which its data-collection efforts were unsuccessful or incomplete, rather than imputing household size or occupancy information from a comparable nearby unit, changes in the Bureau's nonresponse followup procedures could be expected to have much more substantial effects on the final population counts. The Bureau's use of hot-deck imputation therefore mitigates rather than increases any danger that might be thought to exist that the data-collection process could be subject to political manipulation.
3. Section 195 should be construed in light of the Census Act as a whole, which confers extremely broad discretion on the Secretary. See 13 U.S.C. 141(a) (Secretary may conduct the decennial census "in such form and content as he may determine"); Wisconsin v. City of New York, 517 U.S. 1, 19 (1996) (noting that in Section 141(a), "Congress has delegated its broad authority over the census to the Secretary"). Section 195's ban on sampling in the apportionment context does not reflect a systematic congressional effort to micromanage the census; it is instead a focused exception, confined to a particular statistical methodology, to a general rule of broad deference to the Secretary's judgment and expertise. Because hot-deck imputation is not (and was not in 1957) regarded within the statistical community as a form of "sampling," the determination whether imputation shares practical shortcomings similar to those of sampling is entrusted to the Secretary, not to the courts.
C. The Census Bureau Has Consistently Interpreted Section 195 Not To Prohibit Imputation, And Congress Has Not Disapproved That Understanding
1. In holding that 13 U.S.C. 195 bars the use of sampling in determining the apportionment counts, the Court in House of Representatives relied in part on prior Census Bureau pronouncements construing the statute to impose such a prohibition. See 525 U.S. at 340. By contrast, the Bureau has used count imputation in every census since 1960 and has never expressed any doubt as to its legality. See J.A. 267-275 (Hogan Decl.) (describing the Bureau's use of count imputation in 1960-1990 censuses). Testifying at a 1991 congressional oversight hearing, for example, Census Director Barbara Bryant included imputation in her description of longstanding decennial census procedures:
After all efforts are made through mail, personal interview, repeat visits to each housing unit, talking to neighbors, observation, coverage improvement operations, and so on, to identify and complete the enumeration for every housing unit, we still have a certain level of unfinished work. That is, our address control file contains housing units that have been identified by our enumerators as occupied but for which they were not able to collect population information. We also have housing units where it is not known whether the unit is occupied or vacant. In either of these cases, for the last several censuses, we have determined that the counts are improved if we use a procedure to impute persons for these units, rather than just assume there are no persons in these units.
A.R. C01287 (emphasis added). Similarly, in its formal published report announcing the Secretary's decision not to make a statistical adjustment of the 1980 census figures based on sampling, the Bureau explained that the "1980 census data covering the vast majority of Americans will result from a pure count in the full tradition and practice of actual enumeration." 45 Fed. Reg. 69,373 (1980). The Bureau then described its conduct of the 1980 census, including its use of count imputation. Ibid. (explaining that, after several visits to a housing unit, "[i]f the number of occupants is unknown, an entire set of characteristics for a neighboring household is substituted"); see also A.R. C00679 (General Accounting Office official explains in 1991 that "[d]ue to concerns about the legality of sampling, the Bureau did not use sampling techniques as part of the 1980 census but did impute about 762,000 persons into the census count.").
The Bureau's use of count imputation during the 1980 census is especially significant because it affected the composition of the House of Representatives, with Florida receiving a Representative that would have been apportioned to Indiana if imputation had not been used. In the ensuing litigation in Orr v. Baldrige, No. IP-81-604-C (S.D. Ind. July 1, 1985) (J.A. 110-119), the Bureau explained its justifications for using imputation and the basis for its interpretation that imputation is not a form of "sampling" within the meaning of Section 195, and the district court issued an opinion endorsing the Bureau's view of Section 195 that would surely have come to the attention of Congress. See J.A. 89-97 (Affidavit of Barbara A. Bailar filed in Orr (Bailar Aff.)); J.A. 110-119 (Orr district court opinion).7
2. Notwithstanding the Census Bureau's use of count imputation in every decennial census starting in 1960, and its longstanding interpretation that imputation is not a form of "sampling" within the meaning of Section 195, appellants repeatedly suggest (see Br. 6-7, 15, 18, 20, 22) that the Bureau's current construction of Section 195 represents an eleventh-hour reversal precipitated by this Court's decision in House of Representatives. Appellants' argument on that score rests almost exclusively on misleading partial quotations from the Bureau's August 1997 Report to Congress concerning the 2000 census. See Appellants' Br. 15, 18, 20, 22. The full passage is as follows:
In our common experience, "sampling" occurs whenever the information on a portion of a population is used to infer information on the population as a whole. We use samples every day to characterize a larger group-for manufacturing quality checks, for medical tests, for determining air and water quality, and for conducting audits, to name a few. In laymen's terms, a "sample" is taken whenever the whole is represented by less than the whole. Among professional statisticians, the term "sample" is reserved for instances when the selection of the smaller population is based on the methodology of their science.
A.R. C00155 (emphasis added).
As the underscored language makes clear, the Bureau's understanding of "sampling" as a technical term of art reflected in the 1997 Report to Congress does not encompass imputation. Under the hot-deck method, each individual "donor" unit is used because it bears a particular relation to a unit for which the Bureau is (for whatever reason) unable to obtain complete and consistent population data. After the census has been completed, it is possible to identify the "donor" units that were used in the imputation process and to characterize the class of persons within those units, taken together, as a subset of the national population. But the class (qua class) of persons within the donor units is simply the fortuitous result of the Bureau's inability to obtain pertinent information regarding other particular residences. The class is not (in statistical terminology) a "sample" because it is not selected "based on the methodology of [statistical] science" (Report to Congress, A.R. C00155) and does not reflect a "deliberate and purposeful activity occurring during the design phase of a survey" (J.A. 260 (Hogan Decl.)).8
3. The Bureau's longstanding interpretation that hot-deck imputation is not a form of "sampling" within the meaning of 13 U.S.C. 195 is entitled to judicial deference under the principles announced in Chevron U.S.A. Inc. v. NRDC, 467 U.S. 837, 842-845 (1984). Compare House of Representatives, 525 U.S. at 340-341 (noting that the Commerce Department did not invoke principles of Chevron deference in that case in light of the agency's changing views on the question whether Section 195 prohibits the use of "sampling" in the determination of apportionment figures). Deference to the Bureau's reading of the disputed language is particularly appropriate for at least four reasons. First, Section 195 was enacted in 1957 at the request of the Secretary of Commerce, see House of Representatives, 525 U.S. at 336; the Bureau's use of count imputation beginning in the 1960 census thus reflects the contemporaneous understanding of the agency that had proposed the pertinent statutory language that Section 195's prohibition on "sampling" for purposes of apportionment does not encompass imputation. See Norwegian Nitrogen Prods. Co. v. United States, 288 U.S. 294, 315 (1933). Second, because Congress utilized a term of art having an established meaning within the statistical community, interpretation of Section 195 rests in part on a technical judgment as to which the Bureau possesses substantial expertise. Third, deference to the Bureau on this question is consistent with the overall thrust of the Census Act, which vests the Secretary with very broad authority to conduct the decennial census "in such form and content as he may determine." 13 U.S.C. 141(a); see City of New York, 517 U.S. at 19; pp. 23-24, supra.
Fourth, deference to an agency's interpretation of disputed statutory language is especially appropriate where, as here, Congress has amended other provisions of the relevant law without disturbing the settled agency practice regarding the matter in question. See, e.g., United States v. Rutherford, 442 U.S. 544, 554 n.10 (1979) ("[O]nce an agency's statutory construction has been fully brought to the attention of the public and the Congress, and the latter has not sought to alter that interpretation although it has amended the statute in other respects, then presumably the legislative intent has been correctly discerned.") (internal quotation marks omitted). In 1976, when Congress amended Section 195 without change pertinent to this issue, the Census Bureau had already used imputation for apportionment purposes in two decennial censuses. The Bureau again used imputation in 1980 (with the effect of shifting a Representative from Indiana to Florida, leading to the Orr litigation) and in 1990, and it has repeatedly apprised Congress of that practice. Before the 2000 census, the Bureau presented its plan, including the use of imputation, to relevant congressional committees, the General Accounting Office, the Census Monitoring Board (created by Congress in 1998 to oversee the census), the Inspector General, and numerous advisory committees. See J.A. 280-281 (Hogan Decl.); A.R. C01519, C01731, C01752, C01805, C01818-C01819.
While proposals to use sampling have been highly controversial in Congress and elsewhere over the past two decades -resulting in two decisions by this Court (in City of New York and House of Representatives)-the Bureau's longstanding use of imputation has generated no such controversy, and the only court to address the question found it lawful under Section 195. See J.A. 110-119 (Orr). Against this background, it is especially significant that while Congress has amended the Census Act in other respects on a number of occasions, it has not restricted the Bureau's use of imputation.9 That pattern of congressional acquiescence provides further evidence of the reasonableness of the Bureau's position.
D. The Bureau's Use Of "Occupancy" And "Status" Imputation Does Not Violate Section 195
Appellants also contend (Br. 30-35) that, even if "household size" imputation is permissible, Section 195 forbids the use of "occupancy" or "status" imputation. See pp. 6-7, supra (describing three forms of imputation). "Occupancy" and "status" imputation were used "[w]hen Census Bureau records indicated that a housing unit existed but not whether it was occupied or vacant," and "[w]hen the Census Bureau's records had conflicting or insufficient information about whether an address represented a valid, nonduplicated housing unit." J.A. 255 (Hogan Decl.); see p. 7, supra. Appellants' argument lacks merit.
1. The Census Bureau employed "household size" imputation "when Bureau records indicated that the housing unit was occupied, but did not show the number of individuals residing in the unit." J.A. 255 (Hogan Decl.); see J.A. 444; p. 6, supra. In that situation, the Bureau drew the imputed data from a comparable housing unit in the same tract. J.A. 256-257 (Hogan Decl.). Appellants' basic textual theory- that any "statistical procedure in which information on a portion of a State's population * * * is used to infer information about unobserved segments of the population," Appellants' Br. 19 (internal quotation marks omitted), is a form of "sampling" within the meaning of Section 195- would, if accepted, compel the conclusion that "household size" imputation may not be used for purposes of apportionment. Appellants offer no alternative definition of "sampling" that would encompass "occupancy" and "status" imputation while excluding "household size" imputation.
The real thrust of appellants' argument on this score is simply that, in their view, "occupancy" and "status" imputation are less likely to improve the accuracy of the census than is "household size" imputation. Such differences in accuracy would, if established, be relevant to the question whether a decision by the Bureau to use "occupancy" or "status" imputation was arbitrary or capricious under the APA; but they are irrelevant (on appellants' own theory) to the question whether those methods are prohibited by Section 195. Appellants sought to raise an APA challenge in the district court, but the court held that claim to be non-justiciable (see J.S. App. 9a, 12a-15a), and appellants did not contest that ruling on appeal. Appellants' attack on "occupancy" and "status" imputation is simply an attempt to revive that claim under the guise of a Census Act challenge.
2. The policy arguments favoring "household size" imputation are particularly strong, since in that context the alternative to imputation-attributing zero residents to a housing unit that is known to be occupied-will produce demonstrably inaccurate results with respect to every unit. The Bureau's considered judgment, however, is that "occupancy" and "status" imputation will also increase the accuracy of the census. That view is supported by the Bureau's longstanding experience and by ample scientific evidence. After analyzing the 1980 census imputation procedures, for example, the Bureau concluded in 1988 that "data on the correlations between neighboring units indicated that using a previously processed unit would be much more accurate in predicting occupancy status than leaving the questionnaires as vacant." J.A. 213; see also A.R. C01287 (Census Bureau Director explains in 1991 that "for the last several censuses, we have determined that the counts are improved if we use ['household size' and 'occupancy' imputation] * * * rather than just assume there are no persons in these units") (quoted at p. 25, supra).
3. Contrary to appellants' suggestion (Br. 8, 9), the Bureau's use of "status" imputation did not involve "phantom housing units." All of the units for which "status" imputation was used were at addresses included in the Bureau's Decennial Master Address File (DMAF). See J.A. 256 (Hogan Decl.). Indeed, approximately 75% of those units had been added to the DMAF during the 2000 census by field enumerators or by respondents themselves. See J.A. 445-446. Although various data-processing problems resulted in the absence of particular data for those "census adds," the Bureau had a substantial basis for regarding those units as valid residential addresses. See J.A. 446-447; compare Franklin, 505 U.S. at 806.
III. THE CENSUS BUREAU'S USE OF IMPUTATION IS CONSISTENT WITH THE CENSUS CLAUSE OF THE CONSTITUTION
Appellants contend that even if the Census Act authorized the Secretary to use imputation in the census in 2000 (and the four preceding decades), the Constitution barred Congress from authorizing the Secretary to do so. Appellants' contention is inconsistent with the text and structure of the Constitution, the debates in the Constitutional Convention, the history of the implementation of the Census Clause by Congress and the Secretary, and the constitutional goal of equal representation. Whatever limitations the Census Clause may place on other methodologies, it does not prohibit the use of imputation to correct for missing, incomplete, or contradictory data as part of a traditional, household-by-household census.
A. The Text Of The Census Clause Does Not Prescribe A Particular Method Of Determining The Population
Appellants' contention that the Constitution bars the use of imputation rests entirely on the presence of the word "Enumeration" in the Census Clause of the Constitution. That word was not intended, however, to place rigid limitations on Congress in providing for the manner in which the decennial census will be conducted, and in particular it does not prohibit the use of the widely accepted statistical methodology of imputation.
The Oxford English Dictionary (OED) gives as its primary definition of the word "enumeration" "[t]he action of ascertaining the number of something; esp. the taking [of] a census of population; a census." 3 OED 227 (1933). The OED states that the word "enumeration" has been used in that manner since at least 1577. Ibid. The Bureau's use of imputation in the 2000 census indisputably was part of a method "of ascertaining the number of" persons-"a census of population"-within each State.
The structure of Article I, Section 2, Clause 3, reinforces the conclusion that the Framers did not intend to prescribe a particular census methodology. The first sentence of the Clause states that "Representatives * * * shall be apportioned among the several States * * * according to their respective Numbers." The next sentence of the Clause provides: "The actual Enumeration shall be made within three Years after the first Meeting of the Congress of the United States, and within every subsequent Term of ten Years, in such Manner as [Congress] shall by Law direct." The Clause's use of the definite article ("The actual Enumeration") presumes that the concept of an "Enumeration" refers back to or is implicit in what has come before - i.e., in the requirement that the apportionment of Representatives be based upon the States' "respective Numbers"-rather than a further constraint on the discretion of Congress (such as a specification of the means by which those numbers are to be determined).
Thus, the first sentence of Article I, Section 2, Clause 3 states the principle that apportionment of Representatives will be based on the respective total populations of the States, and the first portion of the next sentence then specifies when the ascertainment of those total populations will "actual[ly]" occur, in order to carry the constitutional principle into effect. That understanding is supported by the contemporaneous understanding of the word "actual." See S. Johnson, A Dictionary of the English Language (1755) ("That which comprises action"; "Really in act; not merely potential"; "In act; not purely in speculation"). The means by which the "Enumeration" will be "made" are addressed not by that first portion of the sentence (including the words "actual Enumeration"), but by the second portion, which simply provides that the task will be accomplished "in such Manner as they [Congress] shall by Law direct." Those are words of authorization, not limitation.
The conclusion that the word "Enumeration" in the Census Clause does not impose a rigid limitation on the manner in which the "respective Numbers" of the States are ascertained is reinforced by Article I, Section 9, Clause 4 of the Constitution, which provides that "[n]o Capitation, or other direct, Tax shall be laid, unless in Proportion to the Census or Enumeration herein before directed to be taken." The phrase "Census or Enumeration herein before directed to be taken" can only be understood to refer to the "actual Enumeration" mandated by Article I, Section 2, Clause 3. Article I, Section 9, Clause 4 is significant in two respects. First, by providing that a direct tax must be "in Proportion to the Census or Enumeration," the Clause uses the term "Census or Enumeration" to refer to the respective total populations of the States (and territories), rather than to the process by which those populations are to be ascertained. Cf. Loughborough v. Blake, 18 U.S. (5 Wheat.) 317, 321-322 (1820). The Framers' use of the word "Enumeration" in that distinct sense undermines appellants' contention that the word had a settled and precise meaning and necessarily refers in the Census Clause to a specific method of determining the States' "Numbers." See also note 11, infra.
Second, the Capitation Clause's reference to a "Census or Enumeration" strongly indicates that the Framers used the word "enumeration" as synonymous with "census" of population. See Loughborough v. Blake, 18 U.S. (5 Wheat.) at 321 (describing Article I, Section 2, Clause 3 as providing for a "census" and observing that "[t]he census referred to is admitted to be a census exhibiting the numbers of the respective States"); The Federalist No. 36, at 220 (Hamilton) (C. Rossiter ed. 1961) ("An actual census or enumeration of the people must furnish the rule."). We may assume that the Framers anticipated that the census they povided for would be a systematic undertaking to ascertain the States' populations, and that some methodologies for determining those populations might vary so substantially from what could reasonably be regarded as a "Census or Enumeration" as to violate the Constitution. But while the Census Clause may preclude Congress from supplanting a census with a completely different method of ascertaining state populations, nothing in the constitutional text suggests that the household-focused hot-deck imputation that the Census Bureau has used since 1960 cannot be a legitimate part of a systematic "Census" or "Enumeration." "As a rule the Constitution speaks in general terms, leaving Congress to deal with subsidiary matters of detail as the public interest and changing conditions may require." Nixon v. United States, 506 U.S. 224, 230 (1993) (internal quotation marks omitted).
B. The Drafting History Of The Constitution Confirms That The Framers Did Not Intend To Prescribe A Particular Method Of Taking The Census
In Wesberry v. Sanders, 376 U.S. 1, 10-14 (1964), this Court summarized the debates at the Constitutional Convention concerning the basis upon which the representation of the States in Congress would be determined. Delegates from the larger States argued that each State's representation should be determined on the basis of population; those from the smaller States contended that each State should have an equal number of Representatives. Id. at 10-11. The dispute was finally resolved by means of the Great Compromise, under which representation in the Senate was divided evenly among the States, while the Members of the House of Representatives were "apportioned among the several States . . . according to their respective Numbers." Id. at 13 (quoting U.S. Const. Art. I, § 2, Cl. 3). The Court in Wesberry further observed that "[t]he Constitution embodied Edmund Randolph's proposal for a periodic census to ensure 'fair representation of the people,' an idea endorsed by Mason as assuring that 'numbers of inhabitants' should always be the measure of representation in the House of Representatives." Id. at 13-14 (footnote omitted).
The drafting history of the Census Clause strongly indicates that the Framers did not regard the word "Enumeration" as mandating any particular means of taking the census. Edmund Randolph made the first specific proposal, moving that the Convention adopt a provision stating "that in order to ascertain the alterations in the population & wealth of the several States the Legislature should be required to cause a census, and estimate to be taken within one year after its first meeting; and every ____ years thereafter-and that the Legisl[ature] arrange the Representation accordingly." 1 The Records of the Federal Convention of 1787, at 570-571 (M. Farrand ed., 1966) (Farrand). Subsequent versions of that provision consistently used the word "census"; none used the word "enumeration." See id. at 575, 594, 595, 600.
The Committee of Detail subsequently prepared a draft Constitution incorporating the resolutions passed by the Convention. Article IV, Section 4 of the draft Constitution directed Congress to "regulate the number of representatives by the number of inhabitants, according to the provisions herein after made, at the rate of one for every forty thousand." 2 Farrand 178. The "provisions herein after made" for determining "the number of inhabitants" were contained in Article VII, Section 3 of the draft, which provided:
The proportions of direct taxation shall be regulated by the whole number of white and other free citizens and inhabitants, of every age, sex and condition, including those bound to servitude for a term of years, and three fifths of all other persons not comprehended in the foregoing description, (except Indians not paying taxes) which number shall, within six years after the first meeting of the Legislature, and within the term of every ten years afterwards, be taken in such manner as the said Legislature shall direct.
Id. at 182-183 (emphasis added). The effect of those provisions, read together, was that Congress was directed to "regulate the number of representatives by the number of inhabitants, * * * which number shall * * * be taken in such manner as [Congress] shall direct." The relevant provisions of the Committee of Detail's draft imposed no restriction on the "manner" in which the "number" of each State's inhabitants would be "taken."
After receiving the Committee of Detail's report, the Convention devoted approximately one month to section-by-section analysis of the draft Constitution. See 2 Farrand 190-564. The provisions set forth above were amended in minor respects not relevant here. See id. at 219-223, 339, 350-351, 357. Those provisions were approved by the Convention in their amended form, and the revised draft Constitution was referred to the Committee of Style and Arrangement. See id. at 565, 566, 571.
The Committee of Style reorganized the provisions relevant here, moving the provision for ascertaining the number of inhabitants from a separate article dealing solely with direct taxation to an earlier article dealing with both the apportionment of Representatives and direct taxation. 2 Farrand 590. The words "actual Enumeration" first appeared in that draft, to introduce a sentence that (like the Census Clause as finally adopted) had the principal purpose of specifying when the respective numbers of the States would actually be ascertained (within three years after the first meeting of Congress and every ten years thereafter). No delegate suggested that the Committee of Style's introduction of the words "actual Enumeration" was intended to affect the scope of Congress's authority to conduct the census in the manner that it believed appropriate. Indeed, the text of the Committee's proposal weighs strongly against such an inference, for it carried forward the provision that the task will be performed "in such manner as they [Congress] shall by law direct." Id. at 590-591.
This drafting history indicates that the Framers regarded the "caus[ing]" of a "census," the "tak[ing]" of each State's "number," and the "ma[king]" of "[t]he actual Enumeration" as interchangeable concepts. The perceived equivalence between a "census" and an "enumeration" reflects the Framers' expectation that the States' "number[s]" would be ascertained by means of a systematic undertaking, but it does not suggest an intent to limit Congress's choice of census methodologies. See pp. 34-35, supra.
This Court has recognized that "the Committee of Style had no authority from the Convention to alter the meaning" of the draft Constitution submitted for its review and revision. Nixon, 506 U.S. at 231; accord Powell v. McCormack, 395 U.S. 486, 538-539 (1969). The limited nature of the Committee of Style's mandate does not mean that the Committee's changes "c[an] be disregarded." Appellants' Br. 48. In interpreting ambiguous provisions of the Constitution in its final form, however, the Court "must presume that the Committee's reorganization or rephrasing accurately captured what the Framers meant in their unadorned language" -i.e., "that the Committee did its job." Nixon, 506 U.S. at 231. Because the word "Enumeration" is susceptible of different meanings-and because the structure of both the Census Clause and the Capitation Clause as reported by the Committee of Style cuts against appellants' interpretation (see pp. 33-34, 34-35, supra)-the phrase "actual Enumeration" should be construed in a manner that renders it consistent with the language previously approved by the Convention, which stated simply that the "number" of persons within each State "shall * * * be taken in such manner as the said Legislature shall direct." 2 Farrand 183, 571; compare 3 OED at 227 (explaining that the word "enumeration" has long been used to mean "[t]he action of ascertaining the number of something"); p. 33, supra.10
The fact that the Census Clause uses the word "actual" in conjunction with "Enumeration" also does not require a particular census methodology. Rather, the words "actual Enumeration" simply referred to the concrete undertaking of determining the population of the States, in order to furnish the data necessary to carry into effect the constitutional rule (set forth in the preceding sentence) that Representatives "shall be apportioned among the several States * * * according to their respective Numbers." See p. 35, supra. The words "actual Enumeration" also serve to distinguish the basis for apportioning Representatives that was to commence within three years of the first meeting of Congress from the temporary allocation set forth in the final sentence of Article I, Section 2, Clause 3, which specified the number of Representatives to which each State would be entitled until the first "enumeration" had been made. Indeed, delegates at the Constitutional Convention used the phrase "actual census" in contradistinction to that provisional apportionment, which was based largely on conjecture about the respective populations of the States. See 1 Farrand 602 (Oliver Elseworth stated that the allocation of taxes on the basis of the provisional apportionment "will be unjust until an actual census shall be made."); ibid. (George Mason "doubted much whether the conjectural rule which was to precede the census, would be as just, as it would be rendered by an actual census.").11
C. Since The First Census, The Populations Used For Apportionment Have Been Based On Information Concerning The Aggregate Number Of Persons In A Dwelling Unit And Have Included Persons Of Whom The Government Lacked "Actual Knowledge"
Relying on certain definitions of "enumerate" and "enumeration" drawn from dictionaries roughly contemporaneous with the Founding, appellants contend that the Census Bureau's use of imputation is inconsistent with "[t]he notion of 'counting "singly," "separately," "number by number," "distinctly," which runs through these definitions.'" Br. 36 (quoting House of Representatives, 525 U.S. at 347 (Scalia, J., concurring in part)). Appellants also contend that imputation "falls short of an actual enumeration" because "the Bureau had no actual knowledge as to the number of occupants that live in a housing unit estimated through this procedure." Br. 37. The federal officials charged with conducting the decennial census have never attempted, however, to contact each of the Nation's residents directly (or literally to count every head). Rather, from the time of the First Congress, the conduct of the decennial census has involved techniques designed to obtain and use reliable information concerning the number of persons residing in particular dwelling units. And while the Bureau and its predecessors have always first attempted to obtain such information from a member of the relevant household, they have long relied on a variety of alternative sources of information when efforts to establish such direct contact are unsuccessful. Imputation is fully consistent with the household-by-household approach traditionally used to conduct the decennial census.
1. The Act providing for the 1790 decennial census stated that each "assistant" was to return to the appropriate United States marshal a schedule identifying all heads of households within the assistant's district, together with the number of persons in each household falling within each of five categories (free white males of sixteen years and upwards, free white males under sixteen years, free white females, all other free persons, and slaves). Act of Mar. 1, 1790, ch. 2, § 1, 1 Stat. 102; see House of Representatives, 525 U.S. at 335. Nothing in the 1790 Act required the marshals or their assistants to report or record individual names. See note 11, supra. Nor did the Act specify the manner in which the relevant information was to be obtained, though it did require "each and every person more than sixteen years of age" to furnish accurate information if questioned by an assistant. § 6, 1 Stat. 103. In ensuing years, "when a member of the household could not be found, census-takers have historically relied on information from neighbors, landlords, postal workers, or other proxies." J.A. 253 (Hogan Decl.); see Act of Mar. 3, 1879, ch. 195, § 8, 20 Stat. 475. In 1964, Congress amended the Census Act to "permit the Bureau to replace the personal visit of the enumerator with a form delivered and returned via the Postal Service." House of Representatives, 525 U.S. at 337.
Thus, the decennial census has traditionally been conducted on a household-by-household rather than individual-by-individual basis. And while the evidence on which the apportionment counts are largely based (e.g., the representation by a head-of-household or proxy respondent that a particular number of persons reside at a particular address, or a mail-in form to the same effect) is generally reliable, it is not absolutely reliable, and it does not give the Census Bureau "actual knowledge" (at least in the sense of direct firsthand observation) of all persons included in the counts. In determining the likely number of residents within a given housing unit, data imputed from a comparable nearby unit are concededly less accurate than information provided by a household member or proxy respondent-hence the Bureau's decision to use imputation only as a last resort. That, however, is simply a difference of degree: the use of imputation does not differ in kind from the federal government's prior reliance on other evidence of household size that, while imperfect, is deemed sufficiently reliable to improve the accuracy of the count.
For this reason, even if the words "actual Enumeration" limit Congress's discretion as to the manner in which the census is conducted, and the word "Enumeration" is read restrictively, the imputation techniques that the Census Bureau has employed beginning with the 1960 census are fully in keeping with traditional practice. Even in 1790, the federal officials charged with conducting the census attempted to ascertain the number of the States' inhabitants "separately," "number by number," "distinctly," or "singly," House of Representatives, 525 U.S. at 347 (opinion of Scalia, J.) (citations to dictionaries omitted), only in the sense of seeking to make separate contact with every household in order to obtain the most accurate possible numbers of persons in each. The 2000 census was based on the same household-by-household approach to ascertaining total population figures. The imputation feature of the 2000 census was employed as a part of an actual count, and only to the extent necessitated by the practical realities of the census. It was not an effort to supplant such a count, nor was it based on "gross statistical estimates." Ibid.
As part of its traditional household-by-household approach, the Bureau sought, through imputation, to increase the accuracy of the total population counts by deriving more accurate figures (as compared to the attribution of zero residents) for those individual dwelling units for which data were missing, incomplete, or contradictory. Consistent with historical practice, the Bureau made extensive efforts in the 2000 census to establish direct contact with an occupant of every housing unit, or with another person having some knowledge of the unit. In employing imputation as a last resort, the Census Bureau has simply expanded the range of evidence that may be used to ascertain the number of residents of a particular unit when the Bureau is unable to obtain complete and consistent information from the unit's occupants. Nothing in the text or history of the Census Clause suggests that the Framers sought to preclude Congress from authorizing the Census Bureau to make that sort of expert judgment or to limit the types of evidence on which Congress and the Bureau may rely.12
2. Appellants contend (Br. 38-46) that the Framers were familiar with various means of estimating the population and deliberately adopted constitutional language that would preclude such techniques. The historical evidence on which appellants rely suggests that the Framers drew a general distinction between systematic empirical efforts to count the population through actual inquiry of the people, and attempts to supply population figures by other means, chiefly by inferences from pre-existing data that had initially been compiled for other purposes. See, e.g., T. Pitkin, Statistical View of the Commerce of the United States of America 582-583 (1835) ("In some of the colonies, * * * actual enumerations were made * * *; while in others, estimates were made, founded upon the number of taxable polls, or the number of the militia."). Although appellants' suggested dichotomy between "counting" and "estimating" the population may serve to identify polar extremes (i.e., to identify a method of determining population that is not itself a census), it provides little help in determining what (imperfect) evidence the Census Bureau may rely upon, as part of an overall effort to count the population, to support an inference that a particular number of persons reside in a particular housing unit.
In their jurisdictional statement, appellants asserted that the relevant historical evidence "shows that the phrase 'actual Enumeration' was understood (in the language of the Framers' day) to prescribe an individualized, person-by-person count of the population based on data from those with first-hand knowledge of the matters reported." J.S. 24. In their brief on the merits, however, appellants retreat from their earlier advocacy of an "individualized, person-by-person count" by acknowledging (Br. 37) that "traditional methods of enumeration have always included gathering data from heads of households on individuals not physically present." Appellants' merits brief also contains no reference to a requirement that population data be obtained from persons "with first-hand knowledge of the matters reported." Appellants' seeming abandonment of a "first-hand knowledge" test is well-advised, since federal officials in conducting the census have long relied on proxy respondents who may lack such knowledge.13 But appellants' continued tinkering with their proposed definition of the word "enumeration" (even as they purport to rely on the word's supposedly settled meaning during the Founding era) underscores the fundamental point that neither the constitutional text itself, nor the purported dichotomy between "counting" and "estimation," identifies the type or quantum of evidence from which the Bureau may infer that a particular number of persons resided in a specific housing unit.
D. The Census Bureau's Use Of Imputation In The Last Five Censuses Has Furthered The Equal Representation Goal Of The Apportionment And Census Clauses
The requirement that a new "Enumeration" be conducted within every ten-year period was intended to ensure that the apportionment of Representatives would continue to correspond to the "respective Numbers" of the "several States." The delegates to the Convention anticipated that westward migration would substantially alter the distribution of the country's population. They wished to avoid replicating the English practice of "rotten boroughs" that resulted from the legislature's refusal to reapportion itself in light of population shifts. See Wesberry, 376 U.S. at 14. The relevant provisions operate together to further "our Constitution's plain objective of making equal representation for equal numbers of people the fundamental goal for the House of Representatives." Wesberry, 376 U.S. at 18; see Montana, 503 U.S. at 463 (referring to "[t]he polestar of equal representation"); Franklin, 505 U.S. at 804, 806 ("constitutional goal of equal representation").
The decennial census can fulfill that purpose, however, only to the extent that it accurately determines the relative population shares of the individual States. To construe the phrase "actual Enumeration" to preclude techniques that enhance the accuracy of the actual count would place the Census Clause at cross-purposes with the related constitutional provisions that the Clause was intended to implement. Appellants do not contest the district court's conclusion (see J.S. App. 25a) that attributing zero residents to each housing unit in question, rather than imputing data from a comparable nearby unit, would reduce the accuracy of the apportionment counts. Appellants find that result unproblematic, contending that "the Census Clause * * * necessarily assumes that all persons who cannot be 'enumerated' will be excluded from the apportionment." Br. 50. The constitutional goal of "equal representation for equal numbers of people" is concededly incapable of complete achievement in practice because (inter alia) the population figures derived from the decennial census "are inherently less than absolutely accurate." Gaffney v. Cummings, 412 U.S. 735, 745 (1973); cf. City of New York, 517 U.S. at 6 ("Although each [decennial census] was designed with the goal of accomplishing an 'actual Enumeration' of the population, no census is recognized as having been wholly successful in achieving that goal."). Appellants' construction of the Census Clause, however, would artificially exacerbate the inherent imperfections of the census by preventing the Bureau from attributing any occupants to a dwelling observed as part of the census.
Appellants argue (Br. 41-43) that imputation is inconsistent with what they assert was the intent of the Framers to mandate a particular method of ascertaining the population in order to prevent political manipulation of the census. As explained above (see p. 23, supra), imputation as implemented by the Census Bureau in 2000 and prior decades in fact guards against political manipulation in the design and implementation of followup techniques. In any event, appellants' effort to read a barrier to imputation into the Census Clause on that basis has no support in the historical record. When they believed it necessary to do so, the Framers specifically addressed particular issues concerning the goal of equal representation in the Constitution itself. Thus, the Framers considered and rejected a proposal that the apportionment of Representatives be based in part upon wealth. See pp. 36-37, supra. The requirement that Representatives be apportioned among the States "according to their respective Numbers," U.S. Const. Art. I, § 2, Cl. 3, precludes Congress from adopting a rule of apportionment based on any factor other than population. The Framers also repeatedly expressed concern that Members of Congress might seek to perpetuate themselves in power by declining to reapportion the House of Representatives in light of population shifts. See p. 46, supra. The Framers explicitly addressed that danger by requiring that a new enumeration be conducted at least once every ten years. U.S. Const. Art. I, § 2, Cl. 3. Neither the text nor the history of the Census Clause, however, reveals a comparable intention to circumscribe Congress's selection of methods of taking the census. To the contrary, the Constitution gives Congress broad authority to conduct the decennial census "in such Manner as they shall by Law direct." Ibid.; see City of New York, 517 U.S. at 19 (recognizing that "[t]he text of the Constitution vests Congress with virtually unlimited discretion in conducting the decennial 'actual Enumeration,'" and that "there is no basis for thinking that Congress' discretion is more limited than the text of the Constitution provides").14
This Court's decision in Franklin confirms the breadth of that authority. In identifying the State to which each individual should be allocated as of the decennial census date (now April 1), the Bureau has always relied on the individual's "usual residence" as of that date, even where the person is physically located in a different State on April 1. See Franklin, 505 U.S. at 804 ("The term ['usual residence'] can mean more than mere physical presence, and has been used broadly enough to include some element of allegiance or enduring tie to a place."); id. at 803-806. In implementing the "usual residence" concept, the Bureau has relied in part on general rules, rather than on particularized inquiries into each person's circumstances or subjective loyalties or preferences; and in some instances those general rules have changed over time. See id. at 805-806. As a result, even when specific individuals have been located and identified, the process by which they are allocated to particular States may involve an element of generalization regarding particular classes of persons (e.g., college students), based on judgment or "estimation," as well as an exercise of discretion by the federal officials charged with conducting the census. Indeed, in Franklin itself, the Court concluded that the Secretary's decision to assign overseas military personnel to particular States according to a uniform rule, which resulted in the addition of 922,819 individuals to the state population totals and affected the apportionment of Representatives, reflected a judgment that was "consonant with, though not dictated by, the text and history of the Constitution." 505 U.S. at 806. There is no sound basis for concluding that Congress may not also authorize the Secretary to use imputation techniques as a last resort at the data-processing stage of the census to address problems of missing, incomplete, or contradictory data on a household-by-household basis.
The judgment of the district court should be affirmed.
THEODORE B. OLSON
ROBERT D. MCCALLUM, JR.
Assistant Attorney General
EDWIN S. KNEEDLER
Deputy Solicitor General
MALCOLM L. STEWART
Assistant to the Solicitor
MARK B. STERN
MICHAEL S. RAAB
JONATHAN H. LEVY
1 "'Cold-deck' imputation uses information from a prior census or some other outside source." J.A. 256 (Hogan Decl.).
2 Appellants do not press their APA claim in this Court.
3 Dr. Sukhatme further explained:
It is almost instinctive for a person to examine a few articles, preferably from different parts of a lot, before he or she decides to buy it. No particular attention is, however, paid to the method of choosing articles for examination. A wholesale buyer, on the other hand, has to be careful in selecting articles for examination as it is important for him to ensure that the sample of articles selected for examination is typical of the manufactured product lest he should incur in the long run a heavy loss through wrong decision. * * * A sampling method, if it is to provide a sample representative of the population, must be such that all characteristics of the population, including that of variability among units of the population, are reflected in the sample as closely as the size of the sample will permit, so that reliable estimates of the population characters can be formed from the sample.
Sukhatme, supra, at 1. That description makes clear that the process of "selecting" a sample to which Dr. Sukhatme referred involves a conscious and deliberate effort, during the design phase of a survey, to identify a subset of the relevant population that is believed to be representative of the whole, and to collect data only from that subset.
4 See also H.R. Rep. No. 1043, 85th Cong., 1st Sess. 10 (1957) ("The purpose of section 195 in authorizing the use of sampling procedures is to permit the utilization of something less than a complete enumeration, as implied by the word 'census,' when efficient and accurate coverage may be effected through a sample survey."); Amendment of Title 13, United States Code, Relating to Census: Hearing on H.R. 7911 Before the House Comm. on Post Office and Civil Service, 85th Cong., 1st Sess. 7 (1957) (Commerce Department's Statement of Purpose and Need explains that "[i]nformation obtained through a survey adds to the census data without the increase in costs which would result by obtaining related information on a complete census basis"); Department of Commerce and Related Agencies Appropriations for 1958: Hearings Before a Subcomm. of the House Comm. on Appropriations, 85th Cong., 1st Sess. 679 (1957) (Census Bureau Director explains, with respect to the census of occupation and industry, that "[i]f we can find, say, that a 25-percent sample gives accurate results for what is wanted, we have cut down the work to an important extent").
5 The other sampling procedure at issue in House of Representatives -Integrated Coverage Measurement-likewise would have involved the deliberate use of more intensive data-collection efforts for housing units within the sample than were employed at other, comparable units. See 525 U.S. at 325.
6 Appellants also contend (Br. 28-29) that Congress could not have intended to ban sampling while allowing imputation because sampling is always more reliable than imputation. In determining whether a particular form of either sampling or imputation will increase the accuracy of the census, the pertinent question is "Compared to what?" With respect to sampling, the appropriate comparison is with alternative data-collection measures. Imputation, by contrast, is used only after all efforts to obtain complete and accurate data have failed, and the alternative to imputation is simply the attribution of zero residents to the relevant unit. In any event, for the purposes of determining whether hot-deck imputation violates the Census Act, the only relevant question is whether imputation is a form of "the statistical method known as 'sampling,'" 13 U.S.C. 195, which it is not. The relative accuracy of imputation and sampling in the quite different contexts in which they are used is irrelevant.
7 The government's affiant in Orr explained, in terms consistent with the Bureau's current interpretation:
Sampling is used where a scientifically selected set of units can be used to represent the entire population from which they are drawn and inferences to the entire population can be based on sample results. Imputation is a procedure for determining plausible value[s] for missing data. Imputation is used in both sample surveys and censuses with the goal of achieving as complete as possible an enumeration of the sampled or population units.
J.A. 92-93 (Bailar Aff.).
8 Appellants also attach significance (see Br. 22) to the fact that the 1997 Report to Congress contains a discussion of imputation under the subheading "Reliance on Sampling in Previous Censuses." A.R. C00155. The discussion itself, however, does not state or in any way imply that the Bureau regards imputation as a form of "sampling." Rather, that discussion is offered to support the proposition that "Census 2000 will not be the first time that the Census Bureau has used statistical methods to correct for problems in physical enumeration and to provide a more accurate final result." Ibid. (emphasis added). Later in the same paragraph, the Report to Congress uses the term "sampling" with specific reference to the 1970 Postal Vacancy Check. Ibid. Unlike the imputation processes at issue here, the Postal Vacancy Check did involve the conscious selection of certain housing units for more intensive data-collection efforts than were employed at other, comparable units. See A.R. C00404; J.A. 269 (Hogan Decl.).
9 See, e.g., Act of Oct. 9, 1998, Pub. L. No. 105-252, 112 Stat. 1886; Paperwork Reduction Act of 1995, Pub. L. No. 104-13, 109 Stat. 163; Census Address List Improvement Act of 1994, Pub. L. No. 103-430, 108 Stat. 4393; Act of Oct. 12, 1993, Pub. L. No. 103-105, 107 Stat. 1030; Foreign Direct Investment and International Financial Data Improvements Act of 1990, Pub. L. No. 101-533, 104 Stat. 2344; Act of Nov. 5, 1990, Pub. L. No. 101-506, 104 Stat. 1339; Act of Oct. 27, 1986, Pub. L. No. 99-544, 100 Stat. 3046; Act of Oct. 14, 1986, Pub. L. No. 99-467, 100 Stat. 1192.
10 In Nixon, the Court construed Article I, Section 3, Clause 6 of the Constitution, which provides that "[t]he Senate shall have the sole Power to try all Impeachments." See 506 U.S. at 229. The Court rejected the petitioner's contention that "the word 'sole' has no substantive meaning" because it was added by the Committee of Style. Id. at 231. Even without the word "sole," however, the sentence in question might reasonably have been construed to give the Senate exclusive authority to try impeachments; the Committee of Style's addition of that word could therefore be understood as clarifying rather than altering the meaning of the earlier draft. By "presum[ing] that the [Style] Committee's reorganization or rephrasing accurately captured what the Framers meant in their unadorned language," ibid., the Court was therefore able to read the pertinent provision in a way that was faithful both to the draft Constitution and to the text as finally agreed to by the Convention. In the present case, by contrast, appellants do not contend that the draft language adopted by the Committee of Detail could reasonably be construed to require a particular method of determining the population. Their argument thus reduces to the assertion that the Committee of Style added a substantive limitation on Congress's authority that the earlier draft did not impose. That theory is inconsistent with the "presum[ption] that the Committee [of Style] did its job." Ibid.
11 The Act of Congress providing for the first decennial census used the word "enumeration" in ways that also did not refer to a particular method of conducting the census. The Act began by stating "[t]hat the marshals of the several districts of the United States shall be, and they are hereby authorized and required to cause the number of the inhabitants within their respective districts to be taken; omitting in such enumeration Indians not taxed, and distinguishing free persons, including those bound to service for a term of years, from all others." Act of Mar. 1, 1790, ch. 2, § 1, 1 Stat. 101. That language suggests that the First Congress regarded the concept of "enumeration" as synonymous with that of "caus[ing] the number of the inhabitants * * * to be taken." The Act also required each marshal to take an oath pledging that "I will well and truly cause to be made, a just and perfect enumeration and description of all persons resident within my district, and return the same to the President of the United States." Ibid. (emphasis added). The requirement that the marshal "return" to the President the "enumeration and description" of the people within his district suggests that "enumeration" was used there to refer to the final product of the census-i.e., the population totals themselves-as distinct from the process by which those totals were derived. That understanding is confirmed by Section 3 of the Act, which provided for the Marshals to transmit to the President only "the aggregate amount of each description of persons within their respective districts." 1 Stat. 102 (emphasis added). Finally, Section 1 of the 1790 Act stated that "[t]he enumeration shall commence on the first Monday in August next, and shall close within nine calendar months thereafter," 1 Stat. 101-language suggesting that the word was used there to denote the conduct of the census, although not any particular methodology.
12 By contrast, the sampling procedures at issue in House of Representatives-particularly Integrated Coverage Measurement, see 525 U.S. at 325-326-were designed to increase accuracy at higher levels of aggregation but not to improve household-level accuracy, and they were not part of a comprehensive household-by-household approach.
13 A landlord, for example, might inform the Census Bureau that four persons resided in a particular unit on the census date, based on the lease-signer's prior representation that four persons would be living in the unit, even if the landlord had dealt exclusively with a single individual. A postal worker might inform the Bureau that a unit housed four residents, based on his recollection that mail addressed to four different individuals was regularly delivered to that location on or around the census date.
14 Appellants' assertion (Br. 47) that "the Framers understood an actual enumeration as a specific method of determining the population" also ignores the fact that the Bureau and its predecessors have used a variety of methods (e.g., visits by federal enumerators to individual residences, mailed questionnaires, information from proxy respondents) to determine the number of persons within particular dwelling units. In 1964, for example, Congress repealed the prior requirement that enumerators visit every residence within their districts, see p. 3, supra, thereby allowing the Bureau to rely on mailed questionnaires as the primary form of evidence regarding the extent and distribution of the population. See J.A. 268 (Hogan Decl.) ("In 1970 and each subsequent census, the largest share of the population has been enumerated through the mail-out/mail-back procedure."). It is strange to suppose that the Framers entrusted to Congress a choice of that fundamental character, yet were sufficiently fearful of political manipulation that they foreclosed the use of imputation as a last-resort measure to fill in gaps for particular housing units that accounted for only 0.4% of the Nation's residents.