

Roger Peng: Sustaining data science — in classrooms, code, and conversations
Aug 26, 2025
Roger Peng, a Professor of Statistics and Data Science at UT Austin and co-host of Not So Standard Deviations, discusses his unique journey in data science. He shares insights from his early projects that shaped his passion for R and the importance of hands-on experience in education. The conversation dives into the dynamics of podcasting and how to maintain meaningful content over time. Roger also emphasizes the evolving roles of programming languages like R and SQL, and the community's pivotal role in shaping the landscape of data science.
AI Snips
Chapters
Books
Transcript
Episode notes
Early R Discovery And First Project
- Roger's first nontrivial analysis was author identification using discriminant analysis on texts.
- He discovered R (version ~0.65) around 1997 as a free alternative to S-PLUS and used it for that project.
Try A Small Project First
- Try a full data project to decide if data science suits you: analyze data, ask a question, and write a report.
- If producing that work doesn't interest you, stop early to avoid costly investments like a degree.
Software As Data Science Glue
- Software serves as the unifying element across diverse data science domains.
- Unlike other fields, software generalizes methods and workflows across many types of data.