Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/339507 
Year of Publication: 
26
Series/Report no.: 
cemmap working paper No. CWP01/26
Publisher: 
Centre for Microdata Methods and Practice (cemmap), The Institute for Fiscal Studies (IFS), London
Abstract: 
We approximate the finite-sample distribution of impulse response function (IRF) estimators that are just-identified with a weak instrument using the conventional local-to-zero asymptotic framework. Since the distribution lacks a mean, we assess bias using the mode and conclude that researchers prioritizing robustness against weak instrument bias should favor vector autoregressions (VARs) over local projections (LPs). Existing testing procedures are ill-suited for assessing weak instrument bias in IRF estimates, and we propose a novel simple test based on the usual firststage F-statistic. We investigate instrument strength in several applications from the literature, and discuss to what extent structural parameters must be restricted ex-ante to reject meaningful bias due to weak identification.
Subjects: 
Local Projections
Vector Autoregressions
Instrumental Variables
Weak Instruments
Impulse Responses
Dynamic Causal Effects
JEL: 
C32
C36
Persistent Identifier of the first edition: 
Document Type: 
Working Paper

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.