JSM 2005 Online Program

Abstract #303718

This is the preliminary program for the 2005 Joint Statistical Meetings in Minneapolis, Minnesota. 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, 2005); 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.

The Program has labeled the meeting rooms with "letters" preceding the name of the room, designating in which facility the room is located:

Minneapolis Convention Center = “MCC” Hilton Minneapolis Hotel = “H” Hyatt Regency Minneapolis = “HY”

Back to main JSM 2005 Program page

Legend:

= Applied Session,

= Theme Session,

= Presenter

Activity Number:	178
Type:	Topic Contributed
Date/Time:	Monday, August 8, 2005 : 2:00 PM to 3:50 PM
Sponsor:	Section on Bayesian Statistical Science
Abstract - #303718
Title:	Decision Models for Data Disclosure Limitation Problems
Author(s):	Trottini Mario*+
Companies:	University of Alicante
Address:	Dpto Estadistica e IO, Alicante Ap correos 99, 03080, Spain
Keywords:	Disclosure limitation ; Statistical Confidentiality ; Data Safety ; Data Validity ; Intruder Behaviour
Abstract:	We provide a theoretical framework to aid statistical agencies in the design of dissemination policies involving data collected under pledges of confidentiality. The framework formalizes the comparison of alternative forms of data release as a multiple objective Bayesian decision problem. A decisionmaker (the agency) has to choose the best action (data release) in a class of possible actions taking into account the conflicting objectives: "maximize safety" and ``maximize validity" of the released data. This framework extends previous work on confidentiality by Duncan and Lambert (1986) and is closely related to the approach illustrated in Etzioni and Kadane (1993) for the evaluation of experimental designs when the design and experiment are performed by different parties. We show existing (ad hoc) measures of safety and validity and selection criteria are special cases of our Bayesian modeling for suitable choices of the model's inputs. This exercise enhances our understanding of current practices and illustrates the potential for multiple objective decision theory as a workable tool in statistical confidentiality.

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 2005 program