Review of Economics and Statistics
Instrumental variable (IV) methods are widely used to identify causal effects in models with endogenous explanatory variables. In many cases, the instrument exclusion restriction that underlies the validity of the usual IV inference is suspect; that is, the instruments are 'plausibly exogenous.' We develop practical methods of performing inference while relaxing the exclusion restriction. These methods provide tools for applied researchers who want to proceed with less-than-perfectly valid
... erfectly valid instruments. In addition, our framework enables a concise description of the tradeoff between instrument strength and the degree of exclusion restriction violation. We illustrate the approach with empirical examples that examine the effect of 401(k) participation upon asset accumulation, price elasticity of demand for margarine, and returns-to-schooling. We find that inference is quite informative even with a substantial relaxation of the exclusion restriction in two of the three cases. . We thank seminar participants at the University of Chicago, Brown University, and Brigham Young University for helpful comments. We also appreciate the comments of referees and the editor.