Testing Subspace Granger Causality


The methodology of multivariate Granger non-causality testing at various horizons is extended to allow for inference on its directionality. This paper presents empirical manifestations of these subspaces and provides useful interpretations for them. It then proposes methods for estimating these subspaces and finding their dimensions utilizing simple vector autoregressive models. The methodology is illustrated by an application to empirical monetary policy.
Forthcoming Econometrics and Statistics