Generating synthetic geocoding information for public release

Abstract

"In recent years more and more statistical agencies started collecting detailed geocoding information for some of their surveys or administrative databases. This information enables researchers to define their own geographical levels when investigating spatial effects. Furthermore, detailed geocoding information can be used to link data from different sources. However, these additional research opportunities come at the price of increased risks of re-identification. For this reason external researchers usually cannot get access to the detailed geocodes. Generating synthetic data is an innovative approach for disseminating data to the public with high utility and low risks. In our paper we compare three different strategies for generating synthetic geocodes. (...) Our evaluations are based on a subset of the Integrated Employment Biographies (IEB), a rich administrative data source at the Institute for Employment Research (IAB)." (Text excerpt, IAB-Doku) ((en))

Cite article

Hu, J. & Drechsler, J. (2015): Generating synthetic geocoding information for public release. In: S. A. Europäische Kommission (Hrsg.) (2015): NTTS - Conferences on New Techniques and Technologies for Statistics. Brussels, 9-13 March 2015. Proceedings, p. 56-59.