Editorial for the special issue on: SUNOVA 2012

Abstract

Statistical methods and models assuming the existence of not directly observable or “latent” variables are extensively used in every modern research area. This Special Issue, inspired by the Workshop “ Statistics with Unobservable Variables ” (SUNOVA) held at the University of Brescia as part of the activities of the Research Center “ Data Methods and Systems ” on May 15, 2012, highlights the opportunities offered by some of the most advanced statistical approaches that make use of these types of variables. The short papers submitted by the authors adopt different approaches, models and algorithms to “discover” latent variables (Structural Equation and Factor models, Rasch and Item Response models, Topic models, Non-symmetric CA, Non-linear PCA, Partial Least Squares-PM), with applications in various research fields (healthcare, psychometrics, education, finance, management and bibliometrics). It was a pleasure for us to have the opportunity to read these interesting studies, and we wish to express our thanks to all the authors and reviewers that have made possible this special issue dedicated to the Workshop SUNOVA 2012.