Structural Estimation Under Misspecification: Theory and Implications for Practice

Previous versions of this paper circulated with the titles “Included and Excluded Instruments in Structural Estimation” and “Causal Interpretation of Structural IV Estimands.” We acknowledge funding from the National Science Foundation (SES-1654234, SES-1949047, SES-1949066, DGE1745303), the Sloan Foundation, the Brown University Population Studies and Training Center, the Stanford Institute for Economic Policy Research, and the Eastman Professorship at Brown University. We thank our dedicated research assistants for their contributions to this project, Nathan Miller and Matthew Weinberg for help with their code and data, and Dan Ackerberg, Tim Armstrong, Steve Berry, Phil Haile, Jean-François Houde, Larry Katz, Nathan Miller, audiences at the Econometric Society European Meetings, the Cornell/Penn State Econometrics and IO Conference, the Wealth of Nations Lecture (Panmure House, Edinburgh), Universitat Pompeu Fabra, Tulane University, the Econometric Society North American Winter Meetings, the Online Causal Inference Seminar, the Eddie Lunch at the Stanford Graduate School of Business, the University of Pennsylvania, the Nemmers Prize Conference, the CREST-IZA Conference on Labor Market Policy Evaluation, Carnegie Mellon University, the Stanford IO Fest, UC Berkeley, Princeton University, the Cowles Foundation, the IAAE, SITE, and especially discussants Peter Hull and Stephane Bonhomme for helpful comments. All estimates and analyses in this paper based on Information Resources Inc. data are by the authors and not by Information Resources Inc. The views expressed herein are those of the authors and do not necessarily reflect the views of the National Bureau of Economic Research.

• October 18, 2023