出版社：GESIS - Leibniz-Institute for the Social Sciences, Mannheim
摘要：Combining multiple databases with additional information on the same person is increasingly occurring throughout research. In many applications, identifiers have to be encrypted due to privacy concerns. Existing protocols are inefficient in actual research practice since cases with errors in identifiers are almost always in their entirety lost. Therefore, a new protocol for privacy-preserving record linkage with encrypted identifiers allowing for errors in identifiers has been developed by the authors. The results from tests on simulated and actual databases are comparable to non-encrypted identifiers. This new technique will have many practical applications in social research.
