Hello! Welcome to my collection of public educational resources. I’m a big fan of making as many resources as possible public-facing, and here’s a collection of things I’ve developed over the years.

Public Courses

  • GIS in R: A full, free-standing course for doing geospatial analysis and mapping in R. Originally developed as part of a Stanford Political Science graduate course. Assumes only familiarity with R. Includes both instructional materials and exercises.
  • Practical Data Science (in Python): My course on Practical Data Science using Python developed for the Duke Masters in Interdisciplinary Data Science (MIDS) program. Assumes familiarity with basic, vanilla Python, but covers numpy, pandas, jupyter, git and github, dask, and much more. Includes both instructional materials and exercises, and designed to be used by anyone visiting the site.
  • Unifying Data Science: Course website for my Unifying Data Science course developed for the Duke Masters in Interdisciplinary Data Science (MIDS) program. Less free-standing than some of my other courses I’m afraid, but covers causal inference and provides a conceptual framework for understanding how different perspectives on data science relate to one another.

Defensive Programming

I’m a big advocate for training Data Scientists (including social scientists) techniques for writing code in a manner that minimizes the likelihood of errors, and maximizes the likelihood that when errors occur, they will be caught. To that end, I’ve written a number of resources and tutorials for people looking to improve their code:

And a couple papers on replication issues in social science:

Packages

Presentations

  • What Julia Offers Academic Researchers: Presentation on what I view as the amazing potential of the Julia programming language for academic data scientists. Some points in the presentation are a little out of date at this point (e.g. Julia is up to version 1.5), but general points are all still relevant.