JSM 2004 - Toronto

Abstract #301348

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: 71
Type: Topic Contributed
Date/Time: Monday, August 9, 2004 : 8:30 AM to 10:20 AM
Sponsor: Section on Government Statistics
Abstract - #301348
Title: Disclosure Potential in Regression Models: Some Further Results
Author(s): Arnold P. Reznek*+ and T. Lynn Riggs
Companies: U.S. Census Bureau and Chicago Census Research Data Center
Address: CECON/CES Room 206 WP2, Washington, DC, 20233,
Keywords: disclosure risk ; regression ; confidentiality
Abstract:

Previous research by the author has demonstrated that disclosure potential can exist in some types of regression models. Ordinary Least Squares (OLS), logit, probit, and Poisson regression models can present disclosure risks when the right-hand side (explanatory) variables consist entirely of fully interacted dummy (0,1) variables. In these cases, the models essentially produce tables involving the left-hand-side (dependent) variable. This paper extends that research by considering possible disclosure risks in other types of regression models. Examples of types of models to be considered include those with ordered or multicategory dependent variables (e.g., ordered probit, multinomial logit); survivial models; models with correlated error terms, including longitudinal data; and multiequation models. The paper also discusses the formation of measures of disclosure risks in regression models, beyond the criteria used for traditional statistical tables.

  • 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