Using Science and Data To Make a Difference
Ryan Tibshirani’s father is a statistician, but that is not the reason he went into the field. To Tibshirani, statistics is special because of its broad potential to impact almost any domain or field.
“I went into statistics because I enjoy the beauty and elegance of math, but I wanted to feel more closely connected to science and data,” said Tibshirani, assistant professor of statistics in the Dietrich College of Humanities and Social Sciences. “I found my own way to statistics because I loved the subject, but being able to share this passion and publish papers with my father is very special.”
At Carnegie Mellon University, Tibshirani is involved in both undergraduate and graduate teaching and research. In his research, he develops mathematical models that work to understand simple patterns or structures that may be present in complicated data sets. With these models, he can leverage patterns and structures to predict unseen values of data. This concept can be applied to many different scientific domains.
For example, with Roni Rosenfeld, a professor in the School of Computer Science, Tibshirani formed the research group DELPHI, which stands for Developing the Theory and Practice of Epidemiological Forecasting. DELPHI’s goal is to forecasting seasonal epidemics such as influenza and dengue fever. The CMU DELPHI group has built a system that can - at any given time – predict a flu outbreak in the United States. The group has also tailored the system to be able to forecast dengue fever in Brazil.
“Ryan is advancing the state of the art for understanding the complex data that play an increasingly important role in science, industry and society,” said Christopher Genovese, head of the Department of Statistics. “He has made significant contributions in the theory and methodology of high-dimensional data analysis, and he applies those advances to tackle critical problems like disease forecasting. Ryan is truly an indispensable asset to the Statistics Department and to the university.”
Tibshirani’s students believe that he is one of the best around. Sangwon Hyun, a second year Ph.D. student in the Statistics Department and Tibshirani’s teaching assistant, appreciates the way Tibshirani effectively delivers lectures, even with complex subject matters. Hyun feels that this is rare in at the Ph. D. level since the course materials can be hard to deliver effectively due to the layers of technical and mathematical details.
“In addition to delivering lectures masterfully, Ryan also provides good motivation for further study, pays much attention to details of class administration, and is very willing to help students,” Hyun said.
Tibshirani is an also asset to the Statistics Department in many ways. Yu-Xiang Wang, a third year Ph.D. student in machine learning who collaborates with Tibshirani said, “His way of thinking represent the modern view of statistics that incorporates techniques in machine learning, optimization, and theoretical computer science. Only a small number of professors in stats have such combinations and Ryan is probably one of the best among them.”
According to Tibshirani, one of CMU’s best attributes is the collaborative nature of all of its different units, such as the way Computer Science and Statistics Departments worked together to create DELPHI.
“You often hear that various programs at various institutions are inter-disciplinary, but honestly, I didn’t really know what that meant until I came to CMU,” said Tibshirani. “CMU has one of the best Statistics departments around; I feel very fortunate and proud to be here.”
By Elizabeth Jeffries