JSM 2004 - Toronto

Abstract #301475

This is the preliminary program for the 2004 Joint Statistical Meetings in Toronto, Canada. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2004); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2004 Program page
Activity Number: 44
Type: Topic Contributed
Date/Time: Sunday, August 8, 2004 : 4:00 PM to 5:50 PM
Sponsor: Section on Government Statistics
Abstract - #301475
Title: Full Rank Minimal Sufficient Statistics for Disclosure Limitation and Variance Estimation: A Practical Way to Release Count Information
Author(s): Yves Thibaudeau*+ and William E. Winkler
Companies: U.S. Census Bureau and U.S. Census Bureau
Address: 4700 Silver Hill Rd., Washington, DC, 20233-9100,
Keywords: Loglinear Model ; Minimal Sufficient Statistic ; Contingency Table ; Disclosure Limitation ; Sampling Variance
Abstract:

Thibaudeau derives a full-rank minimal sufficient statistic (FRMSS) for contingency tables, under the assumption that a hierarchical log-linear model governs the sampling process. The dimensionality of this statistic is equal to the number of degrees of freedom of the model. The objective of the paper is to show that: 1. Selected components of the FRMSS carry much of the information requested by the user, so it is reasonable to release only these components, thereby also limiting information disclosure. 2. The representation of a contingency table by selected FRMSS components lends itself well to the computation of sampling variances for estimators of interest. We conduct simulations to illustrate these results.

  • 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 2004 program

JSM 2004 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2004