A0173
Title: Identification and estimation of dynamic factor models
Authors: Joerg Breitung - University of Cologne (Germany) [presenting]
Matei Demetrescu - TU Dortmund University (Germany)
Abstract: In empirical practice, dynamic factor models are typically estimated by performing a principal component analysis (PCA) on the static factor representation. A two-step PCA estimator and a sequential least-squares approach are proposed to estimate the original dynamic factors that enter the model with a prespecified number of lags. The identification of the dynamic factors subject to the usual normalization restrictions is analyzed, and the consistency of the estimator is established. Furthermore, consistent methods for selecting the number of dynamic factors and the number of lags are discussed.
