Relatrice
Monica Scannapieco
ISTAT
Sommario
This seminar will provide an overview of practical cases within Official Statistics where linking data plays a major role. A specific focus will be dedicated to the current need of Official Statistics to link not only traditional, i.e. structured data, but also partially unstructured data. Internet data are an example in this direction: inferencing a (partial) structure for such data and linking them with traditional statistical registers is one of the current challenges. This is indeed an example of Object Matching, which is a recent frontier of Record Linkage posing new issues about the limited structure-ness of data, which does not permit to rely on defined and known variables.
Bibliografia
Batini, C. and Scannapieco, M. (2016): Data and Information Quality, Series on data-centric Systems and Application, Springer, 2016.
Barcaroli G., Scannapieco M., Summa D. (2016): “On the Use of Internet as a Data Source for Official Statistics: a Strategy for Identifying Enterprises on the Web”, SIEDS 2016 (to be published), 2016.
Zardetto, D., Scannapieco, M. and Catarci, T. (2010). Effective Automated Object Matching. Proceedings of the IEEE International Conference on Data Engineering (ICDE 2010).
Organizzazione
Daniela Cocchi