The advent of "Big Data" has brought with it a rapid diversification of data sources, requiring analysis that accounts for the fact that these data have often been generated and recorded for different reasons. Data integration involves combining data residing in different sources to enable statistical inference, or to generate new statistical data for purposes that cannot be served by each source on its own. This can yield significant gains for scientific as well as commercial investigations.
However, valid analysis of such data should allow for the additional uncertainty due to entity ambiguity, whenever it is not possible to state with certainty that the integrated source is the target population of interest. Analysis of Integrated Data aims to provide a solid theoretical basis for this statistical analysis in three generic settings of entity ambiguity: statistical analysis of linked datasets that may contain linkage errors; datasets created by a data fusion process, where joint statistical information is simulated using the information in marginal data from non-overlapping sources; and estimation of target population size when target units are either partially or erroneously covered in each source.
- Covers a range of topics under an overarching perspective of data integration.
- Focuses on statistical uncertainty and inference issues arising from entity ambiguity.
- Features state of the art methods for analysis of integrated data.
- Identifies the important themes that will define future research and teaching in the statistical analysis of integrated data.
Analysis of Integrated Data is aimed primarily at researchers and methodologists interested in statistical methods for data from multiple sources, with a focus on data analysts in the social sciences, and in the public and private sectors.
Table of Contents
Introduction - Ray Chambers
On secondary analysis of datasets that cannot be linked without errors - Li-Chun Zhang
Capture-recapture methods in the presence of linkage errors - Loredana di Congsiglio, Tiziana Tuoto, Li-Chun Zhang
An overview on uncertainty and estimation in statistical matching - Maruo Scanu, Pier Luigi Conti, Daniela Marella
Auxiliary variable selection in a statistical matching problem - Marcello D'Orazio, Marco Di Zio, Mauro Scanu
Minimal inference from incomplete 2 x 2-tables - Li-Chun Zhang, Raymond L. Chambers
Dual and multiple system estimation with fully and partially observed covariates - Van der Heijden et al.
Estimating population size in multiple record systems with uncertainty of state identification - Davide Di Cecco
Log-linear models of erroneous list data - Li-Chun Zhang
Sampling design and analysis using geo-referenced data - Danila Filipponi, Federica Piersimoni, Roberto Benedetti, Maria Michela Dickson, Giuseppe Espa, Diego Giuliani
Li-Chun Zhang is Professor in Social Statistics at the University of Southampton, UK, Senior Researcher at Statistics Norway, Norway, and Professor in Official Statistics at the University of Oslo, Norway.
Raymond Chambers is Professor of Statistical Methodology at the University of Wollongong, Australia.