• Graduate Program
    • Why study Business Data Science?
    • Research Master
    • Admissions
    • Facilities
    • Browse our Courses
    • PhD Vacancies
  • Research
  • Browse our Courses
  • Events
    • Events Calendar
    • Events archive
    • Tinbergen Institute Lectures
    • Summer School
      • Deep Learning
      • Economics of Blockchain and Digital Currencies
      • Foundations of Machine Learning with Applications in Python
      • Marketing Research with Purpose
      • Modern Toolbox for Spatial and Functional Data
      • Sustainable Finance
      • Tuition Fees and Payment
      • Tinbergen Institute Summer School Program
    • Annual Tinbergen Institute Conference archive
  • Summer School
    • Deep Learning
    • Economics of Blockchain and Digital Currencies
    • Foundations of Machine Learning with Applications in Python
    • Marketing Research with Purpose
    • Modern Toolbox for Spatial and Functional Data
    • Sustainable Finance
  • News
  • Alumni
Home | Events | Weak Instrument Bias in Impulse Response Estimators
Seminar

Weak Instrument Bias in Impulse Response Estimators

  • Location
    Tinbergen Institute Amsterdam, Roeterseiland campus, E5.07
    Amsterdam
  • Date and time

    April 08, 2026
    12:55 - 13:55

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 favour 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 first-stage 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. Joint paper with Karel Mertens.