Factor Analysis for Anonymization

In this paper we propose a new method to anonymize (share relevant and detailed information while not naming names) and protect data sets (minimize the utility loss) based on Factor Analysis. The method basically consists of obtaining the factors, which are uncorrelated, protecting them and undoing the transformation in order to get interpretable protected variables. We first show how to proceed when all variables in the data set need protection and, then, we focus on the case where only a subset of variables has to be protected. Finally, we perform a simulation study to compare the proposed method with two alternative techniques: Microaggregation plus noise addition (which has been recognized as a very powerful method) and one anonymization method recently proposed based on Principal Components Analysis.