A Bayesian Partitioning Approach to Duplicate Detection and Record Linkage
Mauricio Sadinle, Duke University
Record linkage techniques allow us to combine different sources of information from a common population in the absence of unique identifiers. Linking multiple files is an important task in a wide variety of applications, since it permits us to gather information that would not be otherwise available, or that would be too expensive to collect. In practice, an additional complication appears when the data files to be linked contain duplicates. Traditional approaches to duplicate detection and record linkage output independent decisions on the co-reference status of each pair of records, which leads to non-transitive decisions that have to be reconciled in some ad-hoc fashion. The joint task of linking multiple data files and finding duplicate records within them can be alternatively posed as partitioning the data files into groups of co-referent records. We present an approach that targets this partition as the parameter of interest, thereby ensuring transitive decisions. Our Bayesian implementation allows us to incorporate prior information on the reliability of the fields in the data files, which is especially useful when no training data are available, and it also provides a proper account of the uncertainty in the duplicate detection and record linkage decisions. We show how this uncertainty can be incorporated in certain models for population size estimation using a case study on human rights violations during the civil war of El Salvador.