×

Validating distance-based record linkage with probabilistic record linkage. (English) Zbl 1028.68519

Escrig, M. Teresa (ed.) et al., Topics in artificial intelligence. 5th Catalonian conference on AI, CCIA 2002, Castellón, Spain, October 24-25, 2002. Proceedings. Berlin: Springer. Lect. Notes Comput. Sci. 2504, 207-215 (2002).
Summary: This work compares two alternative methods for record linkage: distance based and probabilistic record linkage. It compares the performance of both approaches when data is categorical. To this end, a distance over ordinal and nominal scales is defined. The paper shows that, for categorical data, distance-based and probabilistic-based record linkage lead to similar results in relation to the number of re-identified records. As a consequence, the distance proposed for ordinal and nominal scales is implicitly validated.
For the entire collection see [Zbl 1001.00045].

MSC:

68P15 Database theory
PDFBibTeX XMLCite
Full Text: Link