Skip Header
U.S. flag

An official website of the United States government


Disclosure Avoidance Techniques Used for the 1960 Through 2010 Census

ADRM-2020-007
Laura McKenna

Introduction

The U.S. Census Bureau conducts the decennial censuses under Title 13, U.S. Code, Section 9 mandate to not “use the information furnished under the provisions of this title for any purpose other than the statistical purposes for which it is supplied; or make any publication whereby the data furnished by any particular establishment or individual under this title can be identified; or permit anyone other than the sworn officers and employees of the Department or bureau or agency thereof to examine the individual reports (13 U.S.C. § 9 (2007)).” The Census Bureau applies disclosure avoidance (DA) techniques to its publicly released statistical products in order to protect the confidentiality of its respondents and their data.

Different DA procedures were used for the 1960, 1970, 1980, 1990, 2000, and 2010 decennial censuses’ Public Use Microdata Samples (PUMS). This paper summarizes these historical methods in order to put the ongoing DA modernization effort in context. This history of decennial census disclosure avoidance methods discusses only publicly acknowledged confidentiality edits as noted in official documentation. All of the information in this summary was taken from historical public sources, except as noted. None of the information in this paper is confidential.

There is minimal public documentation of the disclosure avoidance methods used in the 1960 Census. There is no discussion of disclosure avoidance for group quarters (GQ) data in public or internal documents for the 1960, 1970, 1980, 1990, and 2000 Censuses, but the 2010 Census has an additional subsection for that purpose. This paper is focused on microdata files from the censuses. The American Community Survey (ACS) is out of scope.

This history gleans procedures from various types of PUMS that differed in terms of sample size, geographic thresholds, short-form (100 percent) data vs. long-form (sample data), and universe. All publications were based on both people in households and people in GQ.

Top

Back to Header