Sessions For: UMOR MI Inst for Data Science

Description: Many scientists use AI coding tools through a browser — copying and pasting between chat and editor. Agentic tools like Claude Code work differently: they run on your machine, read your project, execute your code, and iterate on errors. This hands-on tutorial covers the pros and cons of using a coding agent and how to begin using Claude Code as an R programmer. We'll look at potential use cases of coding agents for data analysis, improving code reproducibility, and tightening the loop between code outputs and manuscript writing.

Hands-on activities:
Optionally, if you'd like to participate in hands-on exercises in the session, you may wish to purchase a Claude Code plan ($20 for a month of access) and have Claude installed on your computer. However, you may also come without doing this, or with a different agent (like OpenAI's Codex or an open-source tool of your choice)

Reminder: All attendees, please bring a laptop.

Focus: Using AI to improve access to, understanding of, and readiness for working with data.
Description:
This session would focus on helping researchers navigate the early stages of working with data, especially when datasets are large, complex, poorly documented, or unfamiliar. AI can assist with interpreting data dictionaries, summarizing metadata, identifying missing documentation, and making datasets more approachable for new users.
Possible hands-on activities:

Summarize a dataset description or codebook into plain languageGenerate a checklist for evaluating whether a dataset is usable for a projectIdentify likely data limitations or missing documentationDraft questions to ask a data provider or collaboratorUse AI to map dataset fields to possible research questions

Focus: Using AI to support data preparation and quality improvement.
Description:
This session would examine how AI can help researchers think through data cleaning tasks before formal analysis begins. The emphasis would be on using AI as a support tool to identify inconsistencies, plan, clean workflows, document decisions, and generate reusable code templates, while keeping human review central.
Possible hands-on activities:
Identify common data quality issues in a sample datasetDraft a cleaning plan for missing values, duplicates, or formatting inconsistenciesGenerate starter code for basic cleaning steps in Python or RCreate a data cleaning log or documentation templateCompare raw and cleaned data examples to assess impact

Focus: Using AI to support exploratory and early-stage analysis.
Description:
This session would introduce ways AI can assist with foundational analysis tasks, such as summarizing data, identifying patterns, suggesting appropriate baseline methods, and helping interpret descriptive outputs. The goal is not to replace statistical judgment, but to help participants move more efficiently through the first pass of analysis.
Possible hands-on activities:
Generate descriptive summaries of a small datasetAsk AI to suggest appropriate baseline analyses for different data typesDraft code for summary statistics, simple visualizations, or basic modelsCompare multiple candidate approaches for an initial analysisInterpret example outputs and discuss what they do, and do not, mean

Focus: Using AI to critically assess outputs, check reasoning, and strengthen trust in findings.
Description:
This session would focus on using AI as a tool for review rather than solely for generation. Participants would practice checking results for plausibility, identifying possible errors or overclaims, and building habits for validation and reproducibility. This is especially important for avoiding misplaced confidence in AI-assisted work.
Possible hands-on activities:
Ask AI to critique an interpretation of findingsCross-check whether a result matches the stated method or assumptionsGenerate a validation checklist for an analysis workflowIdentify possible sources of bias, confounding, or errorReview examples of flawed outputs and discuss how to catch them

Focus: Using AI to communicate research clearly to different audiences.
Description:
This session would explore how AI can help researchers translate technical work into accessible and audience-appropriate communication. Participants would practice adapting the same core findings for different settings, such as collaborators, community partners, students, leadership, or public-facing summaries.
Possible hands-on activities:
Turn a technical summary into plain-language prose
Draft a short abstract, presentation blurb, or project update
Reframe the same findings for academic vs. non-academic audiences
Generate slide outlines or talking points from key results
Create a first draft of documentation, FAQs, or knowledge-transfer notes