An Empirical Comparison of Weak-IV-Robust Procedures in Just-Identified Models

Instrumental variable (IV) regression is recognized as one of the five core methods for causal inference, as identified by Angrist and Pischke (2008). This paper compares two leading approaches to inference under weak identification for just-identified IV models: the classical Anderson-Rubin (AR) procedure and the recently popular tF method proposed by Lee et al. (2022). Using replication data from the American Economic Review (AER) and Monte Carlo simulation experiments, we evaluate the two procedures in terms of statistical significance testing and confidence interval (CI) length. Empirically, we find that the AR procedure typically offers higher power and yields shorter CIs than the tF method. Nonetheless, as noted by Lee et al. (2022), tF has a theoretical advantage in terms of expected CI length. Our findings suggest that the two procedures may be viewed as complementary tools in empirical applications involving potentially weak instruments.