Objective
We ask whether Medicare’s Hospital Compare (HC) random effects (RE) model correctly assesses AMI hospital mortality rates when there is a volume-outcome relationship.
Data Sources/Study Setting
Medicare claims on 208,157 AMI patients admitted in 3,629 acute care hospitals throughout the U.S.
Study Design
We compared average adjusted mortality using logistic regression to average adjusted mortality based on the Hospital Compare RE model. We also fit RE models with the same patient variables as in Medicare’s HC mortality model but also included terms for hospital Medicare AMI volume and another model that additionally included other hospital characteristics.
Principal Findings
Hospital Compare’s average adjusted mortality significantly underestimates average observed death rates in small volume hospitals. Placing hospital volume in the HC model significantly improved predictions.
Conclusions
The HC random effects model underestimates the typically poorer performance of low-volume hospitals. Placing hospital volume in the HC model, and possibly other important hospital characteristics, appears indicated when using a random effects model to predict outcomes. Care must be taken to insure the proper method of reporting such models, especially if hospital characteristics are included in the random effects model.
When a binary variable is misclassi…ed, the measurement error is necessarily negatively correlated with the truth. Consequently, linear instrumental variable methods that treat it as endogenous deliver in ‡ated causal estimates, resulting from attenuated …rst stage coe¢ cients. In this paper, I propose an approach based on para-
Studies of organizational learning and forgetting identify potential channels through which the firm's production experience is lost. These channels have differing implications for efficient resource allocation within the firm, but their relative importance has been ignored to date. We develop a framework for distinguishing the contributions of labor turnover and human capital depreciation to organizational forgetting. We apply our framework to a novel dataset of ambulance companies and their workforce. We find evidence of organizational forgetting, which results from skill decay and turnover effects. The latter has twice the magnitude of the former. (JEL D23, D83, J24, J63)
The effect of shift structure on worker performance and productivity is of increasing interest to firms and regulatory bodies. Using approximately 743,000 emergency medical incidents attended by 2,381 paramedics in Mississippi, we evaluate the extent that paramedics' performance toward the end of shifts is impacted by shift length. We find evidence that performance deteriorates toward the end of long shifts, and argue that fatigue is the mediating factor. Our calculations imply that such deterioration may result in a 0.76 percent increase in 30-day mortality. These findings have implications for workforce organization, calling attention to regulation designed to limit extended work hours. (JEL J22, J24, J28, J45, M12)
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.