and Harvard/MIT industrial organization seminars provided numerous helpful comments, as did Edward Glaeser, Lawrence Katz, and anonymous referees. Also, we would like to thank to Richard Hamer and InterStudy for providing information on HMO enrollment. Funding from the National Science Foundation and the National Institutes on Aging through the NBER is gratefully appreciated. However, all errors are our own. The views expressed herein are those of the authors and not necessarily those of the National Bureau of Economic Research.

We describe an econometric technique, instrumental variables, that can be useful in estimating the effectiveness of clinical treatments in situations when a controlled trial has not or cannot be done. This technique relies upon the existence of one or more variables that induce substantial variation in the treatment variable but have no direct effect on the outcome variable of interest. We illustrate the use of the technique with an application to aggressive treatment of acute myocardial infarction in the elderly.Outcomes research has come to mean many things to many people. To some it means an observational study to establish the consequences of some therapeutic intervention(s), typically using a large administrative data base (12). One of the aims behind the founding of the Agency for Health Care Policy and Research in the late 1980s was to promote such studies in the hope they would inform both coverage decisions in programs such as Medicare as well as improve clinical decision making generally. Many of the Patient Outcome Research Teams (PORTs) supported by the Agency have carried out such studies.To others outcomes research means employing endpoints other than mortality, especially functional status, when evaluating treatment alternatives.

Medical technology is valuable if the benefits of medical advances exceed the costs. We analyze technological change in five conditions to determine if this is so. In four of the conditions--heart attacks, low-birthweight infants, depression, and cataracts--the estimated benefit of technological change is much greater than the cost. In the fifth condition, breast cancer, costs and benefits are about of equal magnitude. We conclude that medical spending as a whole is worth the increased cost of care. This has many implications for public policy.