Abstract #301180

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); 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 2003 Program page
JSM 2003 Abstract #301180
Activity Number: 21
Type: Contributed
Date/Time: Sunday, August 3, 2003 : 2:00 PM to 3:50 PM
Sponsor: Section on Survey Research Methods
Abstract - #301180
Title: Comparison of SMIKe with Data-Swapping and PRAM in Statistical Disclosure Control of Simulated Microdata
Author(s): Fang Liu*+ and Roderick Joseph Little
Companies: University of Michigan and University of Michigan
Address: 2213 Cram Place, Apt. 6, Ann Arbor, MI, 48105-2209,
Keywords: information loss ; disclosure risk ; key variables ; selection ; multiple imputation ; Bayesian
Abstract:

Selective Multiple Imputation of Keys is a newly developed tool for statistical disclosure control (SDC) in microdata. It is model-based with emphasis on satisfactory protection, low-level information loss, and valid statistical inferences. SMIKe releases multiple sets of modified data, rather than just one set, as in data-swapping and post randomization (PRAM). This talk compares these three SDC techniques in a simulation study. The results suggests that SMIKe is a more efficient SDC technique than data swapping and PRAM: information loss in SMIKe can be reduced to negligible levels by increasing the number of modified data sets that are released, and the measure of protection is superior to corresponding measures for data-swapping and PRAM. SMIKe also gives valid statistical inferences based on Reiter's (2003) modification of variance combination rules for multiply-imputed datasets (Rubin 1987). By contrast, data-swapping and PRAM give estimates of parameters with large biases and incorrect coverage probabilities.

  • 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 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003