Data & Analysis Track
Self-paced track · 8 topics · novice → advanced
Work through these on your own, in order or by the topic you need. Each page has a short overview, two hands-on practice activities, a readiness quiz, recommended readings, and useful resources. Everything assumes you’ve done Workshop 1 (prompting and the Drexel data rules).
Difficulty levels
Novice getting started — no prior AI-for-data experience needed. Moderate comfortable with some coding or analysis. Advanced experienced analysts auditing AI-built work.
Suggested path
| # | Topic | Level | You’ll be able to… |
|---|---|---|---|
| 1 | Data Analysis Basics | Novice | Ask questions of a dataset and get a checkable first answer |
| 2 | Data Cleaning, Recoding & Codebooks | Novice | Clean messy data and document it with AI help |
| 3 | Coding with AI | Moderate | Generate, explain, and debug R/Python/Stata code you review |
| 4 | Statistical Interpretation across Stata, R & Python | Moderate | Read output and translate models between languages |
| 5 | AI-Assisted Web & Dashboards | Moderate | Turn data into a shareable dashboard or web page |
| 6 | Image Generation & Annotation | Moderate | Make graphics responsibly and label images for analysis |
| 7 | Qualitative Data Analysis | Moderate | Assist coding and theming without outsourcing interpretation |
| 8 | Data Analysis Advanced | Advanced | Scaffold pipelines and audit their subtle failure modes |
Not sure where to start?
Answer a few questions to find your starting point in this track.
WarningData rules apply throughout
Use public or non-sensitive data for every activity, and match any tool to Drexel’s data classification. See Tools & Access and Drexel’s AI Tools page.