Department of Statistics Unitmark
Dietrich College of Humanities and Social Sciences

Tiffany (Yeukyu) Lee

What is your name?
Tiffany (Yeukyu) Lee

What is your expected graduation year?

What are your expected major(s)/minor(s)?
Major in Statistics, Minor in Computer Science

Where are you from?
Hong Kong

What drew you to the Carnegie Mellon Statistics program?
I started off with a major in Economics, but as coursework progressed, I found myself more drawn towards the Statistical side of Economics, in particular probability theory and modeling. I then made a switch into Statistics during my Sophomore year, and had never regretted my decision. I find beauty in being able to use data to catch a glimpse into the future, and all the professors in Statistics department had made the learning experience fun and enjoyable, not to mention that all the coursework was designed in a way that reflects data analysis in real life. I really enjoy seeing what I learn in classroom has immediate real world impact.

What has been your favorite Statistics class or project so far?
My favorite class was 36-315 Statistical Graphics and Visualization. Unlike traditional data analysis classes, this course aims to teach us how to tell a story using data and relevant tools in doing so. Data visualization is perhaps the easiest way to convey the anomalies of a dataset, and being able to acquire fluency in the visualization tools introduced an entire new perspective to Data Science.

Describe any research experiences or internships that you've had. What did you like best about them?
I continued my work in data visualization in an independent study with Professor Sam Ventura. I built an R package that aims to provide automated linear regression diagnostics plotting with simple syntax. The package was later submitted to the Comprehensive R Archive Network (CRAN) and is now publicly available for download. This was the first time that I had the opportunity to work closely with a professor and get mentorship about an idea about which I was excited.

What are your current plans for after graduation?
I am eager to start working after graduation! In CMU, my academic concentrations are Statistics and Computer Science, but I am nonetheless into Product Design as well. I am hoping to get into the product side of tech companies, where all my skills can be utilized.

Tell us about any CMU student clubs or organizations in which you are involved.
I was a teaching assistant of the course 15-112 Fundamentals of Computer Science and Programming for three semesters. Ever since then I have been devoting my time doing research. I was involved in Articulab (an HCI research lab focuses on conversational agent), and an independent study focusing on statistical software development. Entering senior fall, I am looking forward to begin my senior honors thesis in data wrangling, as well as being a lab assistant in the HCI Institute.

What advice would you give to an incoming student or new Statistics major?
Statistics is big, and it overlaps with an amazing spectrum of subjects such as Biostatistics and Computer Science. Wherever there's data, there must be application of Statistics, so I would definitely encourage students to explore different applications of Statistics and find out what area interests them the most. Carnegie Mellon has a lot of research groups and students organizations that focus on specific parts of Statistics, so students can always get involved to gain hands-on experiences.

How do you like to spend your free time? Do you have any hobbies?
I dearly love hacking and have spent a lot of time coding applications and participating in hackathons. I love to draw and have spent decent amount of time practicing too!

Which movie or TV character best matches your Statistics/Data Science personality?
Probably Neville Longbottom from the Harry Potter series. I don't always make the perfect model, but I try hard and am very honest about the result. 10 points for Gryffindor for integrity, no?

If you could be any statistical distribution, which one would you be and why?
Uniform distribution -- simple and well-known!