7  R and AI Resources

A curated list of resources for learning and using R, and for working with AI as part of your data-science practice. Nothing here is required reading — but each item below has earned its place. Skim it now, bookmark it, and return as you go.

7.1 Resources for learning and using R

7.1.1 IDEs for R

RStudio remains the most widely used IDE for R, and, like R, it is open-source. Its “Help” tab is a gateway to a wide range of R and RStudio resources. However, Posit (the company behind RStudio) has released Positron, a next-generation IDE built for data science with both R and Python. Positron combines the familiar feel of RStudio with the extensibility of VS Code, and includes built-in AI assistance via Positron Assistant. If you’re comfortable with RStudio, stick with it; if you’re curious about a more modern interface or plan to work across R and Python, Positron is worth exploring.

7.1.2 Learning R

Norm Matloff, a computer scientist and statistician at UC-Davis, has a nice, fast introduction to (base) R. He also has interesting takes on base R vs the Tidyverse and the R vs Python debate in data science. For a more in-depth treatment, consult the widely used R for Data Science by Wickham and Grolemund. They will guide you through the Tidyverse. Tidy Data Tutor helps you visualize your data analysis pipelines. James Scott has a great introduction to R that more clearly maps onto BUSN 5000.

You will find a list of econometrics packages for R at the Comprehensive R Archive Network (CRAN). You might prefer the causal inference task view or machine learning task view.

Learning R Markdown or Quarto should go hand-in-hand with learning R. For R Markdown, get started here and keep a cheatsheet handy. You can get started with Quarto here.

7.1.3 Workflow

At least as important as learning R is understanding basic workflow principles. R-bloggers has a beginner’s guide using RStudio Projects. You can find some of the same principles in chapter 2 of Kieran Healy’s Data Visualization book (also linked on the course schedule). Matt Gentzkow and Jesse Shapiro provide a fuller take on workflow principles from the perspective of academic social scientists (also posted on eLC). They even provide a manual for doing as they do.

For a perspective specifically on coding practices in data science education, Pruim, Gîrjău, and Horton (2023) make the case in “Fostering Better Coding Practices for Data Scientists” (Harvard Data Science Review) that good coding habits matter even for beginners. Their argument: it’s far easier to learn good practices alongside R than to unlearn bad habits later. They organize their guidance into a practical top-10 list. Worth reading early in your data-science career.

Suffice it to say that Healy’s book is a great introduction to the wonders of ggplot, which is not R, but indispensable to analysis done in R.

7.2 AI resources

7.2.1 The main AI systems and keeping up with them

Our take is that you should view AI chatbots, like ChatGPT, Claude, and Gemini, as exceedingly productive collaborators with whom you should learn to work, much like you would with a human. Unfortunately, there are no secret prompting strategies or special step-by-step manuals (also like with a human). For some practical guidance along these lines, we recommend that you follow Ethan Mollick’s Substack. If you want to swim in the deeper end of the pool, check out the Substack, Don’t Worry About the Vase.

7.2.2 Coding with AI

One place generative AI really helps is in coding. The chat assistants above can answer coding questions, but for hands-on work you’ll want a tool that lives in — or beside — your editor and can act on your project’s files directly. The landscape moves fast; here are the main options as of mid-2026, ordered roughly from “most built into an R IDE” to “standalone.”

  • Positron Assistant: The assistant built into Posit’s next-generation IDE, Positron (for R and Python). It offers chat, inline edits, completions, and an agent mode, and it can see your live session — loaded data, plots, console history. It is bring-your-own-key: you connect your own Anthropic (Claude), GitHub Copilot, or OpenAI account. Still in preview, but the most R-native option here.
  • GitHub Copilot: The most broadly integrated assistant. It runs in VS Code and Positron and, as an opt-in, in RStudio Desktop. Beyond autocomplete, it now has Ask, Edit, and Agent modes and a model picker spanning current Claude, GPT, and Gemini models. Verified students can often use it free through GitHub Education — check the current eligibility rules, which have changed over time.
  • Claude Code: Anthropic’s agentic command-line tool (also available in VS Code and JetBrains). It reads and edits files across your project, runs commands, and reasons about your whole codebase; a “plan mode” lets you review its approach before it touches anything, and it can connect to external tools and data through the Model Context Protocol (MCP). It runs Claude’s Opus and Sonnet models.
  • OpenAI Codex: OpenAI’s agentic coding tool. It spans a terminal CLI, a VS Code extension, a desktop app, and a cloud agent that runs tasks in the background — all tied to your ChatGPT account — and runs OpenAI’s latest GPT-5-series models. Like Claude Code, it has no native RStudio or Positron integration; you point it at a project folder or use the editor extension.
  • Cursor: An AI-first code editor (a fork of VS Code) with strong autocomplete, multi-file edits, autonomous agents, and a choice of underlying models. It opens an R project like any VS Code workspace via the R extension, but lacks the data-science conveniences of RStudio and Positron. There’s a free tier; heavier use is paid.

7.2.3 Learning more about AI

To learn more about AI, including a comparison of different models, check out Generative AI for Beginners, a free course offered by Microsoft Cloud Advocates. OpenAI and Anthropic have their own AI academies when you want to step it up.