This paper considers the use of instrumental variables to estimate the mean effect of treatment on the treated, the mean effect of treatment on randomly selected persons and the local average treatment effect. It examines what economic questions these parameters address. When responses to treatment vary, the standard argument justifying the use of instrumental variables fails unless person-specific responses to treatment do not influence decisions to participate in the program being evaluated. This requires that individual gains from the program that cannot be predicted from variables in outcome equations do not influence the decision of the persons being studied to participate in the program. In the likely case in which individuals possess and act on private information about gains from the program that cannot be fully predicted by variables in the outcome equation, instrumental variables methods do not estimate economically interesting evaluation parameters. Instrumental variable methods are extremely sensitive to assumptions about how people process information. These arguments are developed for both continuous and discrete treatment variables and several explicit economic models are presented.

James Heckman is the Henry Schultz Distinguished Service Professor at the University of Chicago and Senior Research Fellow of the American Bar Foundation. The first draft of this paper was written in August, 1995. This research was supported by grants from the (NSF-SBR-93-24108), the Russell Sage Foundation and the American Bar Foundation. I thank Derek Neal for numerous helpful comments on repeated occasions and Richard Blundell, Lars Hansen, Lance Lochner, Robert Moffitt, Jose Scheinkman and two anonymous referees for their helpful comments. The essential point made in this paper appears in Heckman and Robb (1985). Data used in this article is available beginning November 1997 through October 2000 from the author. Department of Economics, University of Chicago. 1126 East 59th Street, Chicago, IL 60637.