Statistics concentrator and master’s alum Jason Zhou was awarded the inaugural Department of Statistics Concurrent Masters Prize in May 2023 (along with alum Virginia Ma). This prize is given annually to the graduating concurrent master’s student who has the best overall performance (as indicated by coursework results), has demonstrated achievements in statistics outside of coursework, and has contributed significantly to the department. To celebrate his award and learn about his thesis research and program highlights, we conducted the following interview (excerpted and edited). Congratulations, Jason!
1. When did you first become interested in statistics?
Zhou: I first thought I would major in economics, but when I took Stat 104 [Introduction to Quantitative Methods for Economics], I was intrigued by the emphasis the course placed on drawing nuanced quantitative conclusions from data and using these conclusions as the basis for making other qualitative arguments. Throughout the course structure, I felt encouraged to deepen my questions and examine my process for making quantitative conclusions. In general, statistics appealed to me as a concentration because I was learning quantitative tools and methods that could be applied to real-world problems.
2. What were a few highlights as a concentrator/master's student in the program? Are there certain mentors, courses, or parts of the program that really shaped your experience and interest in the field?
A clear highlight for both my undergraduate and master’s programs has been how supportive the professors are in the department. The faculty want students to go to their office hours and talk about how statistical thinking can be applied to real-life problems.
In particular, the master’s program was a rewarding experience because its courses included topics that broadened my view of statistics. Seeing the passion that professors have for their teaching motivated me to learn more about these topics. For example, Stat 210 [Probability I] was fun because it proposed a new way of thinking about distributions and introduced the idea of using representation. At the same time, the course rigorized statistical concepts; for example, we used mathematical axioms and tools to show how the concept of probability could be expanded. Stat 211 [Statistical Inference I] was also a formative part of my master’s experience. Prof. Lucas Janson did an excellent job calibrating the level of difficulty of questions on homework and exams so that they were just a little beyond our reach and would lead to further discussion and insights in class.
3. How did you select your thesis project? What questions were you asking?
Before I even started thinking about research, I kept hearing people at Harvard mention the name “Xiao-Li,” which piqued my interest in him and his research. When I read a 2018 paper of Prof. Meng’s on data quality, I was impressed by the idea of creating a mathematical formulation to determine what data quality is for mean estimation. In data science, there is a lot of talk about the “importance of data quality,” but Xiao-Li’s paper explained in detail what data quality means and how it impacts research results. After reading Xiao-Li’s work, I was interested in extending this concept of data quality to other estimators, which led me to my thesis topic: “Data Quality Always Matters: An Analysis of Data Quality for Finite Population Z-Estimators” [Jason’s thesis received the Hoopes Prize and was supervised by Professor Xiao-Li Meng]. My thesis project focused on defining data quality for a broad class of nonlinear estimators. One of the main goals was to show that you still need sufficient data quality for an estimator to converge; in other words, data quantity won’t compensate for having bad quality data. Hopefully, this paper will encourage more researchers to think carefully about the data quantity versus quality trade-off. If I had more time to work on this project, I would explore the topic of methodological inefficiency more and would incorporate more concrete examples and use cases.
4. What are a few things that you will miss the most about your Harvard experience?
I’ll miss two things the most about Harvard: the commitment to learning for learning’s sake and, related to this, the people. Harvard offers the kind of environment in which you can follow your passions and intellectual curiosity, which is incredibly gratifying. Students and faculty at Harvard care deeply about diverse interests, which has encouraged me to learn new skills from others; I even learned ballroom dancing in my senior year (the foxtrot was my favorite)! In college, there’s just such a low activation energy to quickly get involved in fun and rewarding endeavors.
5. What are you looking forward to? What are your short-term goals?
I’ll be living in Chicago for the first time, so I’m excited to explore the culture and try out some deep-dish pizza. I am moving there to work at a Quant Firm called IMC – I’m looking forward to getting started!