|
Activity Number:
|
513
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Government Statistics
|
| Abstract - #303711 |
|
Title:
|
An Overview of Uncertainty Creation to Protect Statistical Data
|
|
Author(s):
|
Paul B. Massell*+
|
|
Companies:
|
U.S. Census Bureau
|
|
Address:
|
4600 Silver Hill Road, Washington, DC, 20233-0001,
|
|
Keywords:
|
disclosure protection ; confidentiality ; data swapping ; cell suppression ; uncertainty analysis ; uncertainty creation
|
|
Abstract:
|
Statistical data releases from statistical agencies (e.g., U.S. Census Bureau) have two basic requirements; usefulness (often at a detailed level) and confidentiality protection. We discuss a few protection techniques that satisfy those requirements, albeit in different ways. Many of our examples will involve two methods used to protect (economic) magnitude data tables. These are cell suppression and a simple type of noise that is added to microdata values. Some of our examples will involve data swapping to protect (demographic) categorical data tables. The common theme is uncertainty creation. The agency needs to determine how much in inherent in the data (e.g., due to sample design) and how much needs to be added (if any) to protect data against clever data intruders. The latter requires estimation of prior data knowledge that the best informed data users can obtain from public sources
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2009 program |
