This workshop explores practical ways to use generative AI across the quantitative research workflow—from study design and measurement to data analysis, verification, and interpretation. The focus is not on “better prompting” for its own sake, but on using AI in ways that preserve methodological judgment and accountability.

The emphasis throughout is on using AI to support professional judgment, not replace it. Topics include:

using AI as a methodological critic during study design;
improving survey and measurement decisions;
auditing and cleaning data;
generating and explaining code or formulas;
comparing analytic approaches and assumptions;
verifying AI-generated code and results;
identifying overclaims and unsupported interpretations.

The central idea is simple: AI can accelerate quantitative work, but it does not transfer responsibility for the quality or defensibility of that work.

Slides: tinyurl.com/coehp-quant-ai

If you are affiliated with COEHP and would like to talk through a specific AI, research, data-analysis, or workflow question, you are welcome to contact me about office hours:

Austin D. Eubanks, Ph.D.
Assistant Director of Research and Programming
Office of Innovation for Education
Email: adeubank@uark.edu

Please avoid sending or uploading FERPA-protected, confidential, or otherwise sensitive data when reaching out or experimenting with public AI tools.