Abstract Details
Activity Number:
|
54
|
Type:
|
Invited
|
Date/Time:
|
Sunday, August 4, 2013 : 4:00 PM to 5:50 PM
|
Sponsor:
|
Survey Research Methods Section
|
Abstract - #307422 |
Title:
|
Encrypted Versus Plain: Comparison of Record Linkages Using Privacy Preserving Probabilistic Record Linkage (P3RL): Results from a Simulation Study
|
Author(s):
|
Adrian Spoerri and Kurt Schmidlin and Marcel Zwahlen*+ and Kerri Clough-Gorr
|
Companies:
|
University of Bern and University of Bern and University of Bern and Institute of Social and Preventive Medicine, University of Bern
|
Keywords:
|
probabilistic record linkage ;
bloom filter ;
privacy preserving ;
pre-processing
|
Abstract:
|
To assess performance of Privacy Preserving Probabilistic Record Linkage (P3RL) with Bloom filter encryption we compared different linkage strategies using real and simulated data. Methods: Real data (N=4486) from a Cancer Registry were linked to simulated data (N=200'000) based on the telephone registry. Names, first names, date of birth, sex, nationality, marital status, zip code and tumor category were used. The cancer cases were partially included into table B (97.8%). Table B was run through a data generation tool to create missing variables and through an error simulation tool to randomly simulate data errors. Several linkages with and without encryption and pre-processing were performed. We adapted GRLS, the linkage software from Statistics Canada, to handle Bloom filter hash codes and calculate dice-coefficients. Results: Record linkages with encrypted and unencrypted names gave similar results (in terms of sensitivity and positive predicted value): 99.3% of the cases in table A were found in B with encrypted and pre-processed names. Discussion: P3RL seems a valid alternative to the use of unencrypted names but needs carefully and locally adapted pre-processing of names.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2013 program
|
2013 JSM Online Program Home
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.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.