Time‐Varying Structural Approximate Dynamic Factor Model

ABSTRACT

This study proposes a time‐varying structural approximate dynamic factor (TVS‐ADF) model by extending the approximate dynamic factor (ADF) model in state‐space form. The TVS‐ADF model considers time‐varying coefficients and a time‐varying variance–covariance matrix of its innovation terms to capture complex economic dynamics. We propose the identification scheme of the common factors in the TVS‐ADF model and derive the identification theory. We also propose an effective Markov chain Monte Carlo (MCMC) algorithm to estimate the TVS‐ADF model. To avoid the overparameterization caused by the time‐varying characteristics of the TVS‐ADF model, we include the shrinkage and sparsification approaches in the MCMC algorithm. Extensive simulation experiments and empirical applications demonstrate the outstanding performance of the TVS‐ADF model.