Meet the FAS faculty: Zhou Fan

Zhou Fan
February 8, 2024

By Abiba Biao

To nominate an FAS faculty member to be featured in this series, please email

Zhou Fan has a way with numbers. With a few equations and computer simulations, he’s able to explore an incredible range of questions from the propagation of information through neural networks, to the genetic underpinnings of complex traits that are deeply connected to how we understand and process data. 

Fan is Assistant Professor of Statistics and Data Science in the Faculty of Arts and Sciences (FAS). His interest in statistics stems from work before his PhD, when he developed tools for analyzing molecular dynamics simulations of proteins as a junior scientist at D. E. Shaw Research. His goal was to develop statistical methods and software that could automatically analyze videos of protein motion, and pinpoint rare events that may be difficult to catch by eye.  

“There’s a lot of noise in these videos, because atoms tend to jiggle around extremely rapidly. Every part of the system is moving all the time, but occasionally, something unusual may happen, and it becomes an interesting statistical question of how to define and identify these kinds of events, Fan said.  

Fan describes his research as being theoretical but motivated by applications, using probability theory and computational algorithms to study questions that may originate in genetics and computational biology. His areas of specialization include random matrix theory, high dimensional statistics, random graphs and networks, and methods inspired by statistical physics.  

 “It’s rewarding when you develop a new method for how to analyze data, or a new algorithm for how to compute with data,” he said, that you can then apply back to the scientific domain that motivated that question.” 

Statistics is a unique discipline that can bridge diverse subjects. We do have our own set of questions, but the problems that we think about are also largely motivated by questions arising in other fields,” he said. It’s partly about understanding what issues are common to these interdisciplinary problems and thinking about how to use principled procedures to try to solve these questions.” 

Currently, much of Fan’s work pertains to understanding the accuracy of statistical procedures in “high-dimensional” applications. Whereas classical statistics typically deal with problems where there are few unknown quantities and enough data to estimate them, high dimensional problems are characterized by having to perform inference about many unknown variables with limited data. These high-dimensional problems are now common across experimental science, and they motivate the study of new statistical phenomena and the development of new data analysis procedures. 

For these developments, Fan was awarded the FAS’s Arthur Greer Memorial Prize, which recognizes outstanding research conducted by ladder faculty members in the social or natural sciences, broadly construed, who are untenured at the time that the work is completed or published.  

Fan said that he was “honored” to have received the prize, saying that it is reflective of the value that the FAS is placing on developments in data science and on interdisciplinary and collaborative research more broadly. 

Fan also attributed his work and successes to his supportive department and colleagues. 

“One of the things I really enjoy and appreciate about our department is that it’s an extremely collaborative environment, where we can openly share ideas,” he said. Many of us have common interests, and we are constantly asking each other the question Hey, what if we think about this problem in this new way?’” 

It’s this same environment that he hopes to create for his undergraduate and doctoral students, drawing inspiration from his department and his past experiences as a student. 

You want to give students the room to explore the question and the ideas on their own,” he said, “but also try to steer them in a good direction. Striking that balance is tricky, but important.” 

Since joining the Statistics and Data Science Department in 2018, Fan has seen how the discipline has evolved, taking part in the department’s transitional growth with discussions about new curriculum, and student and post-doc recruiting. 

For Fan, the most rewarding part of the job is diving deep into research questions while embracing the many obstacles along the way. 

It is a challenging process, and oftentimes, you might hit roadblocks or not know how to solve a problem, but I think that’s also part of what makes research exciting, right? Then, when you finally have that aha moment where you figure out how to solve this question that you’ve been stuck on for a long time,” he said, pausing to take a sip from his coffee. “I guess that’s how progress is made.”