Inference on the New Keynesian Phillips Curve with Very Many Instrumental Variables
Limited-information inference on New Keynesian Phillips Curves (NKPCs) and other single-equation macroeconomic relations is characterised by weak and high-dimensional instrumental variables (IVs). Beyond the efficiency concerns previously raised in the literature, I show by simulation that ad-hoc selection procedures can lead to substantial biases in post-selection inference. I propose a Sup Score test that remains valid under dependent data, arbitrarily weak identification, and a number of IVs that increases exponentially with the sample size. Conducting inference on a standard NKPC with 359 IVs and 179 observations, I find substantially wider confidence sets than those commonly found.
Date: 21 May 2021, 13:00
Venue: Held on Zoom
Speaker: Max-Sebastian Dovi (University of Oxford)
Organising department: Department of Economics
Part of: Macroeconomics Working Group
Booking required?: Not required
Audience: Members of the University only
Editor: Melis Clark