Instrument strength in IV estimation and inference: A guide to theory and practice

Michael Keane and Timothy Neal

Journal of Econometrics, 2023, vol. 235, issue 2, 1625-1653

Abstract: Two stage least squares (2SLS) has poor properties if instruments are exogenous but weak. But how strong do instruments need to be for 2SLS estimates and test statistics to exhibit acceptable properties? A common standard is that first-stage F≥10. This is adequate to ensure two-tailed t-tests have modest size distortions. But other problems persist: In particular, we show 2SLS standard errors are artificially small in samples where the estimate is most contaminated by the OLS bias. Hence, if the bias is positive, the t-test has little power to detect true negative effects, and inflated power to find positive effects. This phenomenon, which we call a “power asymmetry,” persists even if first-stage F is in the thousands. Robust tests like Anderson–Rubin perform better, and should be used in lieu of the t-test even with strong instruments. We also show how 2SLS test statistics typically suffer from very low power if first-stage F is only 10, leading us to suggest a higher standard of instrument strength in empirical practice.

Keywords: Instrumental variables; Weak instruments; 2SLS; Endogeneity; F-test; Size distortion; Anderson–Rubin test; Likelihood ratio test; LIML; GMM; Fuller; JIVE (search for similar items in EconPapers)
JEL-codes: C12 C26 C36 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (36)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0304407623000222
Full text for ScienceDirect subscribers only

Related works:
Working Paper: Instrument Strength in IV Estimation and Inference: A Guide to Theory and Practice (2022)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:econom:v:235:y:2023:i:2:p:1625-1653

DOI: 10.1016/j.jeconom.2022.12.009

Access Statistics for this article

Journal of Econometrics is currently edited by T. Amemiya, A. R. Gallant, J. F. Geweke, C. Hsiao and P. M. Robinson

More articles in Journal of Econometrics from Elsevier
Bibliographic data for series maintained by Catherine Liu ().