Abstract
Operational monetary policy rules are characterized by a parsimonious specification and are therefore prone to specification error when estimated on real data. I devise a policy rule estimation procedure, which is robust to marginal misspecification, and study the effects of specification error in least squares. I find the robust evidence of upward bias in policy inertia in least squares applied to most commonly used Taylor type rule. In effect, least squares learning of a central bank can lead to increasing monetary policy inertia over time.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have