Propensity score matching is a popular way to make causal inferences about a binary treatment in observational data. The validity of these methods depends on which variables are used to predict the propensity score. We ask: "Absent strong ignorability, what would be the effect of including an...

If rational individuals pay the full costs of their decisions about food intake and exercise, economists, policy makers, and public health officials should treat the obesity epidemic as a matter of indifference. In this paper, we show that, as long as insurance premiums are not risk rated for...

Propensity score matching is a popular way to make causal inferences about a binary treatment in observational data. The validity of these methods depends on which variables are used to predict the propensity score. We ask: quot;Absent strong ignorability, what would be the effect of including...

The support for scientific investigation in biomedicine depends in part on the adoption of new knowledge into medical practice. We investigate how a technological advance, in the form of a large and influential 2010 randomized controlled study, changed physician practice in statin (a medication...

New ideas no longer fuel economic growth the way they once did. A popular explanation for stagnation is that good ideas are harder to find, rendering slowdown inevitable. We present a simple model of the lifecycle of scientific ideas that points to changes in scientist incentives as the cause of...

As policymakers consider expanding insurance coverage for HIV+ individuals, it is useful to ask if insurance has any affect on health outcomes; and, if so, whether public insurance is as efficacious as private insurance in preventing premature deaths among HIV+ patients. Using data from a...

We use data from the third National Health and Nutrition Examination Survey to examine the prevalence and determinants of poor nutritional outcomes among American youths. One strength of our analysis is that we focus on an array of nutritional outcomes, and we find in fact that the determinants...

Life tables with specific causes of death, particularly when adjusted for demographic and other personal characteristics, can be important components of cost-effectiveness and other economic studies. However, there are few sources of nationally representative information that can be used to...

New ideas no longer fuel economic growth the way they once did. A popular explanation for stagnation is that good ideas are harder to find, rendering slowdown inevitable. We present a simple model of the lifecycle of scientific ideas that points to changes in scientist incentives as the cause of...

We investigate how the genetic risk of developing Alzheimer's Disease (AD) relates to saving behavior. Using nationally representative data from the 1992-2014 Health and Retirement Study (HRS), we find that genetic predisposition for AD correlates with, but is not causally related to older...