In this paper, we address the issue of spurious correlation in the production of health in a systematic way. Spurious correlation entails the risk of linking health status to medical (and nonmedical) inputs when no links exist. This note first presents the bounds testing procedure as a method to...

There have been many studies of the volume-outcome relationship. In all of these, the unit of analysis is the hospital or physician. However, this level of analysis is mostly limited to the use of in-hospital mortality rates and is particularly sensitive to selective referral. Moreover, the...