Missing Aggregate Dynamics: On the Slow Convergence of Lumpy Adjustment Models

Abstract:

Conventional VAR procedures imply less persistence than there really is when adjustments underlying an aggregate variable are lumpy. The extent to which persistence is underestimated decreases with the level of aggregation, yet convergence is very slow and the bias is likely to be present for sectoral data in general and, in many cases, for aggregate data as well. We propose procedures to correct for the bias and provide various applications. In one of them we find that the different speeds with which inflation responds to sectoral and aggregate shocks disappears once we correct for the missing dynamics.