Skip to content →

R Workshops at Temple University


Please stay tuned for more information on the re-scheduled workshops

The Department of Geography & Urban Studies is pleased to offer a sequence of four full-day workshops in using the R statistical programming language. The sequence begins with Introduction to R and RStudio. This workshop will be useful to those with little to no prior experience with R, and may be safely skipped for those who are ready for more advanced topics such as spatial data handling or machine learning.

These workshops are suitable for:

  • Students and data analysts who learned statistics in SPSS, SAS, or Stata, and want to transition to R.
  • Analysts already working in R who want to explore advanced topics.
  • Analysts unfamiliar with the special concerns of spatial data handling.
  • Programmers who want a quick introduction to common statistical methods.

These workshops will be a heavy lift for those without prior experience in either statistics or a programming language. If this applies to you, please consider registering for Introduction to R and RStudio and speak with your instructor before registering for additional workshops.

March 21: Introduction to R and RStudio

This workshop will help you hit the ground running with R using the popular RStudio IDE, with a focus on the modern approach to data wrangling using the tidyverse. You will learn the basics of the R language and data structures, how to load and manipulate tabular data, and how to create go-to statistical visualizations such as scatterplots and histograms. This workshop will set you up with the core knowledge needed to continue your R journey. Previous experience with any programming language and an understanding of basic statistical concepts will be helpful.

April 4: OLS Regression

This workshop offers an overview of tools for linear regression in R. The workshop provides and experiential overview tools and techniques for regression to participants who have at least basic understanding of multiple regression and are interested in applying that understanding in R.  The course starts with basics of data description, exploration, and visualization in R. It then provides a detailed overview of fitting, interpreting, and diagnosing bivariate models. It then provides an overview of tools and syntax for multiple regression and model specification. The workshop is designed to be applied and practical: as much time as possible will be devoted to having participants either follow operational steps on their own lab computers or implementing models of their own devising. The workshop will also provide a brief introduction common variants and adjuncts of regression (such as logistic modeling, factor, and principle components analysis), demonstrating their basic implementation in R and directing participants for resources for their continued learning.

April 25: Spatial Data

This workshop will give you the core knowledge you need to work with vector spatial data (points, lines, and polygons). There are many different packages for spatial analysis in R, and this workshop will focus on sf (simple features), a package which integrates tightly with the tidyverse. You will learn how to load spatial data from a variety of file formats, take measurements, reproject to new coordinate systems, examine spatial relationships, and construct new geometries. You will also learn how to create maps for exploration and presentation. We will work with United States Census data and other sources.

May 2: Machine Learning

This workshop offers a hands-on overview to participants who are new to machine learning (ML) and are comfortable with R syntax. The course starts with ML basics and takes participants step-by-step through increasingly complex modeling styles, including unsupervised and supervised methods. Most of the workshop time will be spent working through a variety of examples that participants may run simultaneously in their computers. At the end of the course, the participants will be able to implement ML algorithms to process data sets similar to the example data provided in the course.