A Risk-Utility Balancing Approach to Generate Synthetic Microdata

59 mins 56 secs,  215.31 MB,  iPod Video  480x270,  29.97 fps,  44100 Hz,  490.5 kbits/sec
Share this media item:
Embed this media item:


About this item
Image inherited from collection
Description: Khan, A (CSIRO)
Thursday 1st December 2016 - 16:30 to 17:30
 
Created: 2016-12-19 16:07
Collection: Data Linkage and Anonymisation
Publisher: Isaac Newton Institute
Copyright: Khan, A
Language: eng (English)
Distribution: World     (downloadable)
Explicit content: No
Aspect Ratio: 16:9
Screencast: No
Bumper: UCS Default
Trailer: UCS Default
 
Abstract: Generation of synthetic microdata is one of the promising approaches to statistical disclosure control of microdata. Methods for generating synthetic microdata for multivariate continuous variables include noise addition and decomposition of data matrix. We present a framework to generate synthetic data matrix based on resampling from Stiefel manifold and application of Slutsky’s theorem in singular value decomposition. We also derive utility and risk measures based on this theorem and present a risk-utility balancing approach to generate synthetic continuous microdata. We apply our proposed methods to some reference microdata sets and demonstrate the usefulness of our proposed methods.
Available Formats
Format Quality Bitrate Size
MPEG-4 Video 640x360    1.91 Mbits/sec 859.63 MB View Download
WebM 640x360    617.19 kbits/sec 271.00 MB View Download
iPod Video * 480x270    490.5 kbits/sec 215.31 MB View Download
MP3 44100 Hz 249.74 kbits/sec 109.75 MB Listen Download
Auto (Allows browser to choose a format it supports)