Inference with many instruments: When is Anderson–Rubin test still useful?
Date
2025
Authors
Tchatoka, F.D.
Ma, Y.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
Economics Letters, 2025; 257:112702-1-112702-5
Statement of Responsibility
Firmin Doko Tchatoka, Yuguo Ma
Conference Name
Abstract
This paper re-evaluates the Anderson–Rubin (AR) test’s performance in many-instrument settings. While previous work raised concerns about size distortions when the number of instruments grows with sample size, we demonstrate that such distortions primarily arise from using asymptotic approximations in settings where the underlying assumptions for their validity fail to hold. By contrast, implementing the AR test with exact F critical values yields accurate size control — even in high-dimensional settings where the number of instruments is close to the sample size. Monte Carlo simulations confirm these findings.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© 2025 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).