Data Science Tools
Languages, statistics packages, version control, editors, and IDEs: the options and their trade-offs.
DSS Training Materials
Materials from our workshops and beginner’s guides: R, Python, and Stata, and the tools around them. Open to anyone, at your own pace.
Training materials
Materials from our workshops and beginner’s guides: R, Python, and Stata, and the tools around them. Open to anyone, at your own pace.
Show
How this works
Click a hexagon
Each one is a workshop or a guide. Click it and its description and links appear here. The buttons above the grid filter by language or by kind; the center hexagon is for groups who would like a workshop of their own, when live workshops return in 2027.
Workshops
The workshops as a list
Hands-on sessions of two to three hours, each with notes to read online and the materials to download and run. All are self-contained.
Any language
R
R Introduction
Importing and manipulating data, packages, basic analyses, and common graphs. For those new to R.
R Data Wrangling
Preparing messy data, through a real example. Intermediate: a few weeks of R assumed.
R Graphics
ggplot2: layers, aesthetics, scales, facets, and themes. Intermediate.
R Regression Models
Multiple regression, categorical predictors, diagnostics, and model comparison in R.
Python
Python Introduction
The basics of Python, through an example of analyzing text data. For those with little or no Python.
Python Web Scraping
Scraping web pages with popular Python libraries. Intermediate: a few months of Python assumed.
Stata
Stata Introduction
Importing and manipulating data, and descriptive statistics. For those new to Stata.
Stata Data Management
Generating and replacing variables, missing values, types, merging and appending, summary data sets.
Stata Graphics
Univariate and bivariate graphs in Stata: histograms, scatterplots, and more.
Stata Regression Models
Models for continuous and binary outcomes, saving results, and quantities of interest.
Beginner’s guides
The guides as a list
Short, self-contained guides to the tools around the analysis: version control, editors, LaTeX, building a package, and two methods primers.
Git and GitHub: A Beginner’s Guide
Creating and cloning repositories, and Git from the command line.
GitHub Pages: A Beginner’s Guide
A personal website on GitHub Pages, from a template.
Visual Studio Code: A Beginner’s Guide
Installing VS Code, with our recommended settings, keybindings, and shortcuts.
Emacs: A Beginner’s Guide
Installing Emacs with our configuration, and the functions you will use every day.
LaTeX: A Beginner’s Guide
Ways to write LaTeX: Overleaf, VS Code, and Emacs compared, with GitHub and Copilot.
Overleaf: A Beginner’s Guide
Signing up, editing, and collaborating on LaTeX documents online.
Rbuild: Create Your Own Packages in R
Building your own R package: structure, best practice, version control, and RStudio.
Matching and Weighting for Causal Inference
Propensity-score methods for confounding in observational studies: a primer and tutorial.
Web Scraping with Selenium Python
Scraping static and dynamic websites with Selenium Python.
Live workshops return in 2027
We taught workshops from 2011 to 2021 and are bringing them back. When sessions are scheduled, the IQSS events page will list them. Departments, labs, and centers across Harvard and MIT: tell us what you would want, on any of these topics or one of your own.
Elsewhere at Harvard
Training and support from other Harvard groups.
- Center for Geographical AnalysisGIS and spatial analysis: workshops and courses
- FAS Research ComputingThe cluster, and training in using it
- Program on Survey ResearchSurvey design and methods, at IQSS
- Harvard Chan Bioinformatics CoreBioinformatics training
- Digital Arts and HumanitiesDigital methods for the humanities, FAS
- Digital Scholarship Support GroupSupport across the schools
- Research Computing Services, HBSStatistical and data services at the Business School
- Research Support Services, HGSEResearch support at the Graduate School of Education
Further afield
- UCLA statistical methods and data analyticsWorked examples in R, Stata, and more, from UCLA's OARC
- CRANR itself, its packages, and their manuals