Inferential theory for generalized dynamic factor models

Abstract

We provide the asymptotic distributional theory for the so-called General or Generalized Dynamic Factor Model (GDFM), laying the foundations for an inferential approach in the GDFM analysis of high-dimensional time series. By exploiting the duality between common shocks and dynamic loadings, we derive the asymptotic distribution and associated standard errors for a class of estimators for common shocks, dynamic loadings, common components, and impulse response functions. We present an empirical application aimed at constructing a “core” inflation indicator for the U.S. economy, which demonstrates the superiority of the GDFM-based indicator over the most common approaches, particularly the one based on Principal Components.