U.S. flag

An official website of the United States government

Skip Header


Effects on Trend Statistics of the Use of Multiplicative Noise for Disclosure Limitation

Written by:

Background

Historically the Census Bureau has favored disclosure limitation methods that protect sensitive data by limiting the amount of information given out. However, the Bureau is now considering methods that would allow for the release of more information but at the cost of having to distort the data in some way (Zayatz, Moore, and Evans, 1996). In the case of establishment tabular data, the traditional approach has been to suppress the publication of cells that are deemed sensitive, i.e., at risk for disclosing an individual respondent's data. Other cells, called complementary suppressions, must then also be suppressed to prevent the values of sensitive cells from being recovered through addition and subtraction of published cells. (For a complete discussion of cell suppression, see e.g., Federal Committee on Statistical Methodology, 1994.) Cell suppression thus protects sensitive data by limiting the amount of information given in the tables.

Page Last Revised - October 8, 2021
Is this page helpful?
Thumbs Up Image Yes Thumbs Down Image No
NO THANKS
255 characters maximum 255 characters maximum reached
Thank you for your feedback.
Comments or suggestions?

Top

Back to Header