STAT 4000 introduces students across Auburn to data science foundations

Across disciplines at Auburn University, students are looking for ways to better understand the data driven systems that influence business, technology and research. STAT 4000: Introduction to Data Science helps them develop the skills to work confidently with data in their own fields.

Developed and currently taught by Roberto Molinari, assistant professor in the Department of Mathematics and Statistics and co-director of the Statistics and Data Science Program, the course provides a practical introduction to the full data science workflow. Students learn how to clean and wrangle data, visualize patterns, reason about probability and uncertainty, and apply core ideas from supervised and unsupervised learning. They work directly with real datasets using both R and Python, widely used programming languages for data analysis, gaining experience not only with concepts but with the tools used in practice.

Molinari describes the course as a high-level overview of the field that balances conceptual understanding with applied work.

"It’s an opportunity to teach students how you collect data, how you process the data and how you extract meaningful information from it," Molinari said. "Students come out of this having a good understanding of the complexities behind data analysis and how the tools we are using today, including AI, work and what their potential problems are."

Since launching in 2024, the course has grown steadily. It began with roughly two dozen students and has expanded each year, reaching 60 students this semester.

Molinari attributes that growth to increased awareness of how central data literacy has become across disciplines.

"There’s a lot of hype around the term data science, and there’s a good reason for it," Molinari said. "Students have become more aware that companies require employees to know how to manage and process information."

The course draws students from across the university, particularly from the colleges of business and engineering, along with mathematics and computer science majors. That diversity shapes the classroom dynamic. Molinari begins slowly before gradually increasing complexity.

"There’s a low bar at the start, and then it slowly grows to bring everyone along for the more challenging concepts that are toward the end of the course," he said.

Beyond technical skills, Molinari emphasizes a deeper lesson — learning to reason under uncertainty.

"Data are random. There’s a lot of uncertainty in there, and conclusions you draw from them are uncertain," he said. "One of the major things we can learn in college is dealing with uncertainty."

He draws parallels between statistical reasoning and everyday decision making.

"In the long run, you will end up where you’re supposed to be,” he said. “But in the short run, you’re going to have a lot of ups and downs.”

Students say the course delivers both conceptual clarity and practical impact.

Chris Hinkson, now a first-year master’s student in computer science and software engineering, took STAT 4000 during his junior year as an undergraduate. He said the course connected statistical foundations to real machine learning applications.

"STAT 4000 taught me to approach problems in data science and machine learning not just from a computer science perspective but also through the statistical principles and reasoning behind them," Hinkson said.

Destanie Pitt, a senior mathematics major, said the course aligned directly with her interests.

"I really enjoyed probability and statistics,” she explained. “As a math major interested in work with data, I knew it would be really essential for my career.”

She added the randomly assigned final project strengthened her analytical and teamwork skills. She later applied those skills in the Auburn Business Analytics Case Competition, where she and her partner won using techniques learned in STAT 4000.

Carlos Berrios, who completed his bachelor’s degree in computer science in 2024 and expects to finish his master’s degree in 2026, said the course strengthened his statistical foundation.

"Actually learning and seeing the inner workings of neural networks, rather than just accepting them as magic, was valuable to me," Berrios said.

For Molinari, helping students understand what lies beneath modern AI tools is central to the course’s purpose.

"It’s really a way to understand how AI works," he said. "It’s important to understand how to use AI to process information."

Whether students continue into advanced coursework in statistics and machine learning or apply data skills in other disciplines, Molinari said the goal is consistent: to build informed, critical users of data.

"I think it’s a great way of reasoning with information," he said. "It’s a good way to teach people how to think."