Faculty Research Seminar Series

Catherine Wofram - The Demand for Energy-Using Assets among the World's Rising Middle Classes

Catherine Wofram - We study decisions to acquire energy-using assets in the presence of rising incomes. We develop a theoretical framework to show that credit-constrained, poor households are unlikely to use additional income to buy appliances. The effect of income growth on asset purchases is stronger at higher income levels. We use large and plausibly exogenous shocks to household income generated by the conditional-cash-transfer program in Mexico, Oportunidades, to show that asset acquisition is nonlinear, depends, as predicted, on the pace of income growth, and both effects are economically large among beneficiaries. Our results may help explain important worldwide trends in energy use. - Read More

Eva Lee - Optimizing and Transforming the Healthcare System

Sep 29, 2014 at 12:00 PM

Eva Lee - Risk and decision models and predictive analytics have long been cornerstones for advancement of business analytics in industrial, government, and military applications. They are also playing key roles in advancing and transforming the healthcare delivery system. In particular, multi-source data system modeling and big data analytics and technologies play an increasingly important role in modern healthcare enterprise. Many problems can be formulated into mathematical models and can be analyzed using sophisticated optimization, decision analysis, and computational techniques. In this talk, we will share some of our successes in early disease diagnosis, treatment planning design, and healthcare operations through innovation in decision and predictive big data analytics. - Read More

Paul Rosenbaum - Testing one hypothesis twice in observational studies

Oct 06, 2014 from 12:00 PM to 01:30 PM

Paul Rosenbaum - In an observational study of treatment effects, a sensitivity analysis asks about the magnitude of the departure from random assignment that would need to be present to alter the conclusions of an analysis that naively assumed adjustments for measured covariates succeeded in removing all bias. The reported degree of sensitivity to unmeasured biases depends upon both the process that generated the data and the chosen methods of analysis, so a poor choice of method may lead to an exaggerated report of sensitivity to bias. This suggests the possibility of performing more than one analysis with a correction for multiple inference, say testing one null hypothesis using two or three different tests. In theory and in an example, it is shown that the gains in large samples from testing twice will often be large, because testing twice has the larger of the two design sensitivities of the component tests, and the losses due to correcting for two tests will often be small, because two tests of one hypothesis will typically be highly correlated, so a correction for multiple testing that takes this into account will be a small correction. An illustration uses data from the US National Health and Nutrition Examination Survey concerning lead in the blood of cigarette smokers. - Read More