Updates and Information on Coronavirus (COVID-19)

Faculty Spotlight: Chung Eun Lee

January 31, 2018

Chung Eun Lee was attracted by the juxtaposition of statistics and business at the Haslam College of Business.

“The Department of Business Analytics and Statistics was very interesting to me because it’s kind of a mixture of statisticians and management scientists,” she says. “That’s not typically the case statistics departments at other universities.”

Lee joined the Haslam faculty in 2017 as an assistant professor. Previously, she earned a master’s in statistics from Columbia University and her doctorate in statistics from the University of Illinois at Urbana-Champaign. As an undergraduate in her home country of South Korea, Lee double majored in statistics and business — an early combined interest that she’s pursuing again today.

“I hoped to find a department where I could apply statistical analytics tools to data sets,” she says. “I thought Haslam was the best place that I could start, because the statistics department is already linked to business analytics.”

Currently, Lee teaches undergraduate courses in regression modeling and applied time series and forecasting.

“For our final project in the time series course, I ask students to grab a real data set that they’re interested in and use the techniques we learned during the semester to generate some predictions,” she says. “I also ask them to evaluate the accuracy of their predictions.” Lee appreciates the opportunity to introduce her students to real business questions and answers.

“Statistics courses usually focus on the theoretical side, but here students have a chance to work on a real data set right away,” she says. “It’s an interesting activity for them, and they can directly apply what they learned.”

Lee’s research interests center around dimension reduction methods — ways to reduce the size of a large data set while losing minimal information.

“For one part of my dissertation, I worked on developing a new methodology of dimension reduction of multivariate time series for conditional mean and volatility from the aspect of optimal prediction,” Lee says.

In 2016, she published a paper in the Journal of the American Statistical Association based on the project. “Another project I’ve worked on is constructing a new nonparametric conditional mean independence test for functional data.”