Conti, Gabriella6; Frühwirth-Schnatter, Sylvia3; Heckman, James J.7; Piatek, Rémi8
1 Department of Economics, Faculty of Social Sciences, Københavns Universitet2 University College London3 Wirtschaftsuniversität Wien4 University of Chicago5 Økonomisk Institut, Department of Economics, Faculty of Social Sciences, Københavns Universitet6 University College London7 University of Chicago8 Økonomisk Institut, Department of Economics, Faculty of Social Sciences, Københavns Universitet
This paper develops and applies a Bayesian approach to Exploratory Factor Analysis that improves on ad hoc classical approaches. Our framework relies on dedicated factor models and simultaneously determines the number of factors, the allocation of each measurement to a unique factor, and the corresponding factor loadings. Classical identification criteria are applied and integrated into our Bayesian procedure to generate models that are stable and clearly interpretable. A Monte Carlo study confirms the validity of the approach. The method is used to produce interpretable low dimensional aggregates from a high dimensional set of psychological measurements.
Journal of Econometrics, 2014, Vol 183, Issue 1, p. 31-57
Faculty of Social Sciences; Bayesian Factor Models; Exploratory Factor Analysis; Identifiability; Marginal Data Augmentation; Model Selection; Model Expansion