Federal
Committee on Statistical
Methodology Office of Management and Budget |
FCSM
Home ^ Statistical Committees ^ CDAC^ |
Federal statistical agencies and their contractors often collect data
from persons, businesses, or other entities under a pledge of
confidentiality. Before disseminating the results as either public-use microdata
files or tables, these agencies should apply statistical methods to
protect the confidentiality of the information they collect. A review
and evaluation of the statistical disclosure limitation techniques used
by Federal statistical agencies can be found in the Federal Committee on
Statistical Methodology's 1994 report, Report on Statistical
Disclosure Limitation Methodology (Statistical Policy Working Paper
[SPWP] # 22). In addition, SPWP # 22 contains a set of 12
recommendations to improve disclosure limitation practices.
One of the recommendations in SPWP # 22 is that agencies should
centralize their review of disclosure-limited data products. In
discussing this recommendation, SPWP # 22 suggests that if the number of
programs is small, such a review could be handled by one individual;
alternatively, if an agency has multiple or large programs, a review
panel, team, or board might be needed. In this document, the term Disclosure
Review Board is used to refer to the formally or informally
designated unit or individual that handles such review. The attached
document, "Checklist on Disclosure Potential of Proposed Data
Releases" (called Checklist), is one tool that can assist
agencies in reviewing disclosure-limited data products. Completed
Checklists should be submitted to the Disclosure Review Board for
review. Most agency data products are intended for public use, with no
restrictions on eligibility and intended use. Products that meet the
criteria for public release may not have sufficient detail to satisfy
the analytical requirements of all users. Consequently, some agencies
have developed restricted access procedures for making more
detailed microdata files and tables available to some users, subject to
conditions of eligibility, location of use, purpose of use, security
procedures, and other features associated with access to the data. This
Checklist is intended primarily for use in the development of public-use
data products. Some of the disclosure limitation procedures
described in the Checklist may be of value in preparing data products
for restricted access; however, the procedures may have to be relaxed to
some degree to meet users' analytical requirements. The Confidentiality
and Data Access Committee (CDAC) plans to develop additional documents
(perhaps including another checklist) for use in developing arrangements
for restricted releases of microdata files and tables. Pending
availability of these documents, agencies may wish to consult a 1993
article Journal of Official Statistics by Thomas B. Jabine,
entitled "Procedures for Restricted Data Access" (vol. 9, no.
3, pp. 519-590), which summarizes restricted access procedures in use at
that time. The Checklist consists of a series of questions that are designed to
assist an agency's Disclosure Review Board to determine the suitability
of releasing either public-use microdata files or tables from data
collected from individuals and/or organizations under an assurance of
confidentiality. Section 4 pertains to microdata files that contain
information from individuals or establishments, while Sections 5 and 6
refer to tabular data from individuals and establishments, respectively.
This Checklist is based on one used at the U.S. Bureau of the Census. In
creating its Checklist, CDAC has liberally borrowed descriptions and
definitions from SPWP # 22.
|