Prof. Stange’s research uses population administrative education and labor market data to understand, evaluate and improve education, employment, and economic policy. Much of the work involves analyzing millions of course-taking and transcript records for college students, whether they be at a single institution, a handful of institutions, or all institutions in several states. This data is used to richly characterize the experiences of college students and relate these experiences to outcomes such as educational attainment, employment, earnings, and career trajectories. Several projects also involve working with the text contained in the universe of all job ads posted online in the US for the past decade. This data is used to characterize the demand for different skills and education credentials in the US labor market. Classification is a task that is arising frequently in this work: How to classify courses into groups based on their title and content? How to identify students with similar educational experiences based on their course-taking patterns? How to classify job ads as being more appropriate for one type of college major or another? This data science work is often paired with traditional causal inference tools of economics, including quasi-experimental methods.
My research centers on studying the interaction between abstract, theoretically sound probabilistic algorithms and human beings. One aspect of my research explores connections of Machine Learning to Crowdsourcing and Economics; focused in both cases on better understanding the aggregation process. As Machine Learning algorithms are used in making decisions that affect human lives, I am interested in evaluating the fairness of Machine Learning algorithms as well as exploring various paradigms of fairness. I study how these notions interact with more traditional performance metrics. My research in Computer Science Education focuses on developing and using evidence-based techniques in educating undergraduates in Machine Learning. To this end, I have developed a pilot summer program to introduce students to current Machine Learning research and enable them to make a more informed decision about what role they would like research to play in their future. I have also mentored (and continue to mentor) undergraduate students and work with students to produce publishable, and award-winning, undergraduate research.
My broad research interests are in multi-agent systems, computational economics and finance, and artificial intelligence. I apply techniques from algorithmic game theory, statistical machine learning, decision theory, etc. to a variety of problems at the intersection of the computational and social sciences. A major focus of my research has been the design and analysis of market-making algorithms for financial markets and, in particular, prediction markets — incentive-based mechanisms for aggregating data in the form of private beliefs about uncertain events (e.g. the outcome of an election) distributed among strategic agents. I use both analytical and simulation-based methods to investigate the impact of factors such as wealth, risk attitude, manipulative behavior, etc. on information aggregation in market ecosystems. Another line of work I am pursuing involves algorithms for allocating resources based on preference data collected from potential recipients, satisfying efficiency, fairness, and diversity criteria; my joint work on ethnicity quotas in Singapore public housing allocation deserves special mention in this vein. More recently, I have got involved in research on empirical game-theoretic analysis, a family of methods for building tractable models of complex, procedurally defined games from empirical/simulated payoff data and using them to reason about game outcomes.
Catherine H. Hausman is an Associate Professor in the School of Public Policy and a Research Associate at the National Bureau of Economic Research. She uses causal inference, related statistical methods, and microeconomic modeling to answer questions at the intersection of energy markets, environmental quality, climate change, and public policy.
Recent projects have looked at inequality and environmental quality, the natural gas sector’s role in methane leaks, the impact of climate change on the electricity grid, and the effects of nuclear power plant closures. Her research has appeared in the American Economic Journal: Applied Economics, the American Economic Journal: Economic Policy, the Brookings Papers on Economic Activity, and the Proceedings of the National Academy of Sciences.
Rahul Ladhania is an Assistant Professor of Health Informatics in the Department of Health Management & Policy at the University of Michigan School of Public Health. He also has a secondary (courtesy) appointment with the Department of Biostatistics at SPH. Rahul’s research is in the area of causal inference and machine learning in public and behavioral health. A large body of his work focuses on estimating personalized treatment rules and heterogeneous effects of policy, digital and behavioral interventions on human behavior and health outcomes in complex experimental and observational settings using statistical machine learning methods.
Rahul co-leads the Machine Learning team at the Behavior Change For Good Initiative (Penn), where he is working on two `mega-studies’ (very large multi-arm randomized trials): one in partnership with a national fitness chain, to estimate the effects of behavioral interventions on promoting gym visit habit formation; and the other in partnership with two large Mid-Atlantic health systems and a national pharmacy chain, to estimate the effects of text-based interventions on increasing flu shot vaccination rates. His other projects involve partnerships with step-counting apps and mobile-based games to learn user behavior patterns, and design and evaluate interventions and their heterogeneous effects on user behavior.
Cyber-security is a complex and multi-dimensional research field. My research style comprises an inter-disciplinary (primarily rooted in economics, econometrics, data science (AI/ML/Bayesian and Frequentist Statistics), game theory, and network science) investigation of major socially pressing issues impacting the quality of cyber-risk management in modern networked and distributed engineering systems such as IoT-driven critical infrastructures, cloud-based service networks, and app-based systems (e.g., mobile commerce, smart homes) to name a few. I take delight in proposing data-driven, rigorous, and interdisciplinary solutions to both, existing fundamental challenges that pose a practical bottleneck to (cost) effective cyber-risk management, and futuristic cyber-security and privacy issues that might plague modern (networked) engineering systems. I strongly strive for originality, practical significance, and mathematical rigor in my solutions. One of my primary end goals is to conceptually get arms around complex, multi-dimensional information security and privacy problems in a way that helps, informs, and empowers practitioners and policy makers to take the right steps in making the cyber-space more secure.
I am broadly interested in the economics of sports. My current research focuses primarily on two areas, two-sided markets and antitrust policy. Using e-commerce and social media data, I study the effect on consumer and social welfare when sports consumption move from traditional markets to the internet.
I work on the analysis of sports as they relate to economics, business, finance, history, performance modeling, analytics and prediction/forecasting. I typically use panel data econometric techniques to understand team performance in professional sports. I also have interest in forecast models.
Professor Kowalski’s recent research analyzes experiments and clinical trials with the goal of designing policies to target insurance expansions and medical treatments to individuals who stand to benefit from them the most. Her research has also explored the impact of previous Medicaid expansions, the Affordable Care Act, the Massachusetts health reform of 2006, and employer-sponsored health insurance plans. She has also used cutting-edge techniques to estimate the value of medical spending on at-risk newborns.
My research interests lie in design and analysis of randomized controlled trials (RCTs), partial identification, identification and inference with multi-valued treatments and instruments, and quantile regression. In one recent paper I study the optimal stratified randomization procedure in RCTs, and found a certain kind of matched-pair design is optimal. In another paper (coauthored with Joe Romano and Azeem Shaikh), we provide asymptotically exact inference procedure for matched-pair designs. In another paper we study inference with moment inequalities whose dimension grows exponentially fast with the sample size. I also have a paper in which we study the sharp identified sets for various treatment effects with multi-valued instruments and multi-values treatments.